Cross-lingual Transfer of Semantic Role Labeling Models
Kozhevnikov, Mikhail and Titov, Ivan

Article Structure

Abstract

Semantic Role Labeling (SRL) has become one of the standard tasks of natural language processing and proven useful as a source of information for a number of other applications.

Background and Motivation

Semantic role labeling has proven useful in many natural language processing tasks, such as question answering (Shen and Lapata, 2007; Kaisser and Webber, 2007), textual entailment (Sammons et al., 2009), machine translation (Wu and Fung, 2009; Liu and Gildea, 2010; Gao and Vogel, 2011) and dialogue systems (Basili et al., 2009; van der Plas et al., 2009).

Setup

The purpose of the study is not to develop a yet another semantic role labeling system — any existing SRL system can (after some modification) be used in this setup — but to assess the practical applicability of cross-lingual model transfer to this problem, compare it against the alternatives and identify its strong/weak points depending on a particular setup.

Model Transfer

The idea of this work is to abstract the model away from the particular source language and apply it to a new one.

Evaluation

4.1 Datasets and Preprocessing

Results

In order to ensure that the results are consistent, the test sets, except for the French one, were partitioned into five equal parts (of 5 to 10 thousand sentences each, depending on the dataset) and the evaluation performed separately on each one.

Related Work

Development of robust statistical models for core NLP tasks is a challenging problem, and adaptation of existing models to new languages presents a viable alternative to exhaustive annotation for each language.

Conclusion

We have considered the cross-lingual model transfer approach as applied to the task of semantic role labeling and observed that for closely related languages it performs comparably to annotation projection approaches.

Topics

cross-lingual

Appears in 31 sentences as: Cross-lingual (4) cross-lingual (30)
In Cross-lingual Transfer of Semantic Role Labeling Models
  1. This approach is then evaluated on three language pairs, demonstrating competitive performance as compared to a state-of-the-art unsupervised SRL system and a cross-lingual annotation projection baseline.
    Page 1, “Abstract”
  2. Cross-lingual annotation projection systems (Pado and Lapata, 2009), for example, propagate information directly via word alignment links.
    Page 1, “Background and Motivation”
  3. An alternative approach, known as cross-lingual model transfer, or cross-lingual model adaptation, consists of modifying a source-language model to make it directly applicable to a new language.
    Page 1, “Background and Motivation”
  4. (2012) enriches this representation with cross-lingual word clusters, considerably improving the performance.
    Page 1, “Background and Motivation”
  5. However with the help of recently introduced cross-lingual word represen-
    Page 1, “Background and Motivation”
  6. tations, such as the cross-lingual clustering mentioned above or cross-lingual distributed word representations of Klementiev et al.
    Page 2, “Background and Motivation”
  7. In this work we construct a shared feature representation for a pair of languages, employing cross-lingual representations of syntactic and lexical information, train a semantic role labeling model on one language and apply it to the other one.
    Page 2, “Background and Motivation”
  8. The transferred model is compared against two baselines: an unsupervised SRL system and a model trained on the output of a cross-lingual annotation projection system.
    Page 2, “Background and Motivation”
  9. The purpose of the study is not to develop a yet another semantic role labeling system — any existing SRL system can (after some modification) be used in this setup — but to assess the practical applicability of cross-lingual model transfer to this problem, compare it against the alternatives and identify its strong/weak points depending on a particular setup.
    Page 2, “Setup”
  10. With respect to the use of syntactic annotation we consider two options: using an existing dependency parser for the target language and obtaining one by means of cross-lingual transfer (see section 4.2).
    Page 2, “Setup”
  11. This can be achieved either by means of cross-lingual annotation projection (Yarowsky et al., 2001) or by cross-lingual model transfer (Zeman and Resnik, 2008).
    Page 2, “Setup”

See all papers in Proc. ACL 2013 that mention cross-lingual.

See all papers in Proc. ACL that mention cross-lingual.

Back to top.

semantic role

Appears in 19 sentences as: Semantic Role (2) Semantic role (1) semantic role (9) semantic roles (7)
In Cross-lingual Transfer of Semantic Role Labeling Models
  1. Semantic Role Labeling (SRL) has become one of the standard tasks of natural language processing and proven useful as a source of information for a number of other applications.
    Page 1, “Abstract”
  2. Semantic role labeling has proven useful in many natural language processing tasks, such as question answering (Shen and Lapata, 2007; Kaisser and Webber, 2007), textual entailment (Sammons et al., 2009), machine translation (Wu and Fung, 2009; Liu and Gildea, 2010; Gao and Vogel, 2011) and dialogue systems (Basili et al., 2009; van der Plas et al., 2009).
    Page 1, “Background and Motivation”
  3. Multiple models have been designed to automatically predict semantic roles , and a considerable amount of data has been annotated to train these models, if only for a few more popular languages.
    Page 1, “Background and Motivation”
  4. A number of approaches to the construction of semantic role labeling models for new languages
    Page 1, “Background and Motivation”
  5. It clusters together arguments that should bear the same semantic role , but does not assign a particular role to each cluster.
    Page 1, “Background and Motivation”
  6. In this work we construct a shared feature representation for a pair of languages, employing cross-lingual representations of syntactic and lexical information, train a semantic role labeling model on one language and apply it to the other one.
    Page 2, “Background and Motivation”
  7. The purpose of the study is not to develop a yet another semantic role labeling system — any existing SRL system can (after some modification) be used in this setup — but to assess the practical applicability of cross-lingual model transfer to this problem, compare it against the alternatives and identify its strong/weak points depending on a particular setup.
    Page 2, “Setup”
  8. 2.1 Semantic Role Labeling Model
    Page 2, “Setup”
  9. We consider the dependency-based version of semantic role labeling as described in Hajic et al.
    Page 2, “Setup”
  10. Unsupervised SRL models (Lang and Lapata, 2010) cluster the arguments of predicates in a given corpus according to their semantic roles .
    Page 2, “Setup”
  11. The performance of such models can be impressive, especially for those languages where semantic roles correlate strongly with syntactic relation of the argument to its predicate.
    Page 2, “Setup”

See all papers in Proc. ACL 2013 that mention semantic role.

See all papers in Proc. ACL that mention semantic role.

Back to top.

part-of-speech

Appears in 15 sentences as: Part-of-speech (1) part-of-speech (14)
In Cross-lingual Transfer of Semantic Role Labeling Models
  1. (2011) successfully apply this idea to the transfer of dependency parsers, using part-of-speech tags as the shared representation of words.
    Page 1, “Background and Motivation”
  2. We also assume that the predicate identification information is available — in most languages it can be obtained using a relatively simple heuristic based on part-of-speech tags.
    Page 2, “Setup”
  3. (2011), we assume that a part-of-speech tagger is available for the target language.
    Page 2, “Setup”
  4. This setup requires that we use the same feature representation for both languages, for example part-of-speech tags and dependency relation labels should be from the same inventory.
    Page 3, “Model Transfer”
  5. In this study we will confine ourselves to those features that are applicable to all languages in question, namely: part-of-speech tags, syntactic dependency structures and representations of the word’s identity.
    Page 3, “Model Transfer”
  6. Part-of-speech Tags.
    Page 3, “Model Transfer”
  7. We map part-of-speech tags into the universal tagset following Petrov et al.
    Page 3, “Model Transfer”
  8. This may have a negative effect on the performance of a monolingual model, since most part-of-speech tagsets are more fine-grained than the universal POS tags considered here.
    Page 3, “Model Transfer”
  9. The universal part-of-speech tags used in evaluation are derived from gold-standard annotation for all languages except French, where predicted ones had to be used instead.
    Page 3, “Model Transfer”
  10. One could map dependency relations into a simplified form that would be shared between languages, as it is done for part-of-speech tags in Petrov et al.
    Page 3, “Model Transfer”
  11. POS part-of-speech tags Synt unlabeled dependency graph C l s cross-lingual word clusters (31 o s s glossed word forms Depre l dependency relations
    Page 4, “Model Transfer”

See all papers in Proc. ACL 2013 that mention part-of-speech.

See all papers in Proc. ACL that mention part-of-speech.

Back to top.

part-of-speech tags

Appears in 14 sentences as: part-of-speech tag (1) part-of-speech tagger (1) Part-of-speech Tags (1) part-of-speech tags (11)
In Cross-lingual Transfer of Semantic Role Labeling Models
  1. (2011) successfully apply this idea to the transfer of dependency parsers, using part-of-speech tags as the shared representation of words.
    Page 1, “Background and Motivation”
  2. We also assume that the predicate identification information is available — in most languages it can be obtained using a relatively simple heuristic based on part-of-speech tags .
    Page 2, “Setup”
  3. (2011), we assume that a part-of-speech tagger is available for the target language.
    Page 2, “Setup”
  4. This setup requires that we use the same feature representation for both languages, for example part-of-speech tags and dependency relation labels should be from the same inventory.
    Page 3, “Model Transfer”
  5. In this study we will confine ourselves to those features that are applicable to all languages in question, namely: part-of-speech tags , syntactic dependency structures and representations of the word’s identity.
    Page 3, “Model Transfer”
  6. Part-of-speech Tags .
    Page 3, “Model Transfer”
  7. We map part-of-speech tags into the universal tagset following Petrov et al.
    Page 3, “Model Transfer”
  8. The universal part-of-speech tags used in evaluation are derived from gold-standard annotation for all languages except French, where predicted ones had to be used instead.
    Page 3, “Model Transfer”
  9. One could map dependency relations into a simplified form that would be shared between languages, as it is done for part-of-speech tags in Petrov et al.
    Page 3, “Model Transfer”
  10. POS part-of-speech tags Synt unlabeled dependency graph C l s cross-lingual word clusters (31 o s s glossed word forms Depre l dependency relations
    Page 4, “Model Transfer”
  11. For each word, we use its part-of-speech tag , cross-lingual cluster id, word identity (glossed, when evaluating on the target language) and its dependency relation to its parent.
    Page 4, “Model Transfer”

See all papers in Proc. ACL 2013 that mention part-of-speech tags.

See all papers in Proc. ACL that mention part-of-speech tags.

Back to top.

role labeling

Appears in 10 sentences as: Role Labeling (2) role labeling (7) role labels (1)
In Cross-lingual Transfer of Semantic Role Labeling Models
  1. Semantic Role Labeling (SRL) has become one of the standard tasks of natural language processing and proven useful as a source of information for a number of other applications.
    Page 1, “Abstract”
  2. Semantic role labeling has proven useful in many natural language processing tasks, such as question answering (Shen and Lapata, 2007; Kaisser and Webber, 2007), textual entailment (Sammons et al., 2009), machine translation (Wu and Fung, 2009; Liu and Gildea, 2010; Gao and Vogel, 2011) and dialogue systems (Basili et al., 2009; van der Plas et al., 2009).
    Page 1, “Background and Motivation”
  3. A number of approaches to the construction of semantic role labeling models for new languages
    Page 1, “Background and Motivation”
  4. In this work we construct a shared feature representation for a pair of languages, employing cross-lingual representations of syntactic and lexical information, train a semantic role labeling model on one language and apply it to the other one.
    Page 2, “Background and Motivation”
  5. The purpose of the study is not to develop a yet another semantic role labeling system — any existing SRL system can (after some modification) be used in this setup — but to assess the practical applicability of cross-lingual model transfer to this problem, compare it against the alternatives and identify its strong/weak points depending on a particular setup.
    Page 2, “Setup”
  6. 2.1 Semantic Role Labeling Model
    Page 2, “Setup”
  7. We consider the dependency-based version of semantic role labeling as described in Hajic et al.
    Page 2, “Setup”
  8. However, assigning meaningful role labels to the resulting clusters requires additional effort and the model’s parameters generally need some adjustment for every language.
    Page 2, “Setup”
  9. Unsupervised semantic role labeling methods (Lang and Lapata, 2010; Lang and Lapata, 2011; Titov and Klementiev, 2012a; Lorenzo and Cerisara, 2012) also constitute an alternative to cross-lingual model transfer.
    Page 8, “Related Work”
  10. We have considered the cross-lingual model transfer approach as applied to the task of semantic role labeling and observed that for closely related languages it performs comparably to annotation projection approaches.
    Page 8, “Conclusion”

See all papers in Proc. ACL 2013 that mention role labeling.

See all papers in Proc. ACL that mention role labeling.

Back to top.

dependency relations

Appears in 9 sentences as: dependency relation (4) dependency relations (5)
In Cross-lingual Transfer of Semantic Role Labeling Models
  1. This setup requires that we use the same feature representation for both languages, for example part-of-speech tags and dependency relation labels should be from the same inventory.
    Page 3, “Model Transfer”
  2. Most dependency relation inventories are language-specific, and finding a shared representation for them is a challenging problem.
    Page 3, “Model Transfer”
  3. One could map dependency relations into a simplified form that would be shared between languages, as it is done for part-of-speech tags in Petrov et al.
    Page 3, “Model Transfer”
  4. In this work we discard the dependency relation labels where the inventories do not match and only consider the unlabeled syntactic dependency graph.
    Page 3, “Model Transfer”
  5. POS part-of-speech tags Synt unlabeled dependency graph C l s cross-lingual word clusters (31 o s s glossed word forms Depre l dependency relations
    Page 4, “Model Transfer”
  6. For each word, we use its part-of-speech tag, cross-lingual cluster id, word identity (glossed, when evaluating on the target language) and its dependency relation to its parent.
    Page 4, “Model Transfer”
  7. Also included are the sequences of part-of-speech tags and dependency relations on the path between the predicate and the argument.
    Page 4, “Model Transfer”
  8. Also note that the syntactic annotation of English and Czech in PCEDT 2.0 is quite similar (to the extent permitted by the difference in the structure of the two languages) and we can use the dependency relations in our experiments.
    Page 5, “Evaluation”
  9. First of all, both EN-CZ and CZ-EN benefit noticeably from the use of the original syntactic annotation, including dependency relations , but not from the transferred syntax, most likely due to the low syntactic transfer performance.
    Page 8, “Results”

See all papers in Proc. ACL 2013 that mention dependency relations.

See all papers in Proc. ACL that mention dependency relations.

Back to top.

semantic role labeling

Appears in 9 sentences as: Semantic Role Labeling (2) Semantic role labeling (1) semantic role labeling (6)
In Cross-lingual Transfer of Semantic Role Labeling Models
  1. Semantic Role Labeling (SRL) has become one of the standard tasks of natural language processing and proven useful as a source of information for a number of other applications.
    Page 1, “Abstract”
  2. Semantic role labeling has proven useful in many natural language processing tasks, such as question answering (Shen and Lapata, 2007; Kaisser and Webber, 2007), textual entailment (Sammons et al., 2009), machine translation (Wu and Fung, 2009; Liu and Gildea, 2010; Gao and Vogel, 2011) and dialogue systems (Basili et al., 2009; van der Plas et al., 2009).
    Page 1, “Background and Motivation”
  3. A number of approaches to the construction of semantic role labeling models for new languages
    Page 1, “Background and Motivation”
  4. In this work we construct a shared feature representation for a pair of languages, employing cross-lingual representations of syntactic and lexical information, train a semantic role labeling model on one language and apply it to the other one.
    Page 2, “Background and Motivation”
  5. The purpose of the study is not to develop a yet another semantic role labeling system — any existing SRL system can (after some modification) be used in this setup — but to assess the practical applicability of cross-lingual model transfer to this problem, compare it against the alternatives and identify its strong/weak points depending on a particular setup.
    Page 2, “Setup”
  6. 2.1 Semantic Role Labeling Model
    Page 2, “Setup”
  7. We consider the dependency-based version of semantic role labeling as described in Hajic et al.
    Page 2, “Setup”
  8. Unsupervised semantic role labeling methods (Lang and Lapata, 2010; Lang and Lapata, 2011; Titov and Klementiev, 2012a; Lorenzo and Cerisara, 2012) also constitute an alternative to cross-lingual model transfer.
    Page 8, “Related Work”
  9. We have considered the cross-lingual model transfer approach as applied to the task of semantic role labeling and observed that for closely related languages it performs comparably to annotation projection approaches.
    Page 8, “Conclusion”

See all papers in Proc. ACL 2013 that mention semantic role labeling.

See all papers in Proc. ACL that mention semantic role labeling.

Back to top.

language pairs

Appears in 7 sentences as: language pair (2) language pairs (5)
In Cross-lingual Transfer of Semantic Role Labeling Models
  1. This approach is then evaluated on three language pairs , demonstrating competitive performance as compared to a state-of-the-art unsupervised SRL system and a cross-lingual annotation projection baseline.
    Page 1, “Abstract”
  2. We evaluate on five (directed) language pairs —EN-ZH, ZH-EN, EN-CZ, CZ-EN and EN-FR, where EN, FR, CZ and ZH denote English, French, Czech and Chinese, respectively.
    Page 2, “Background and Motivation”
  3. We have identified three language pairs for which such resources are available: English-Chinese, English-Czech and English-French.
    Page 5, “Evaluation”
  4. The data for the second language pair is drawn from the Prague Czech-English Dependency Treebank 2.0 (Hajic et al., 2012), which we converted to a format similar to that of CoNLL-8T1.
    Page 5, “Evaluation”
  5. It is easy to see that the scores vary strongly depending on the language pair , due to both the difference in the annotation scheme used and the degree of relatedness between the languages.
    Page 7, “Results”
  6. The source language scores for English vary between language pairs because of the difference in syntactic annotation and role subset used.
    Page 7, “Results”
  7. For more distant language pairs , the contributions of individual feature groups are less interpretable, so we only highlight a few observations.
    Page 8, “Results”

See all papers in Proc. ACL 2013 that mention language pairs.

See all papers in Proc. ACL that mention language pairs.

Back to top.

parallel data

Appears in 7 sentences as: parallel data (7)
In Cross-lingual Transfer of Semantic Role Labeling Models
  1. The approaches in this third group often use parallel data to bridge the gap between languages.
    Page 1, “Background and Motivation”
  2. However, they are very sensitive to the quality of parallel data , as well as the accuracy of a source-language model on it.
    Page 1, “Background and Motivation”
  3. This approach yields an SRL model for a new language at a very low cost, effectively requiring only a source language model and parallel data .
    Page 2, “Background and Motivation”
  4. We use parallel data to construct a bilingual dictionary used in word mapping, as well as in the projection baseline.
    Page 5, “Evaluation”
  5. The basic idea behind model transfer is similar to that of cross-lingual annotation projection, as we can see from the way parallel data is used in, for example, McDonald et al.
    Page 8, “Related Work”
  6. It allows one to quickly construct an SRL model for a new language without manual annotation or language-specific heuristics, provided an accurate model is available for one of the related languages along with a certain amount of parallel data for the two languages.
    Page 8, “Conclusion”
  7. notation projection approaches require sentence-and word-aligned parallel data and crucially depend on the accuracy of the syntactic parsing and SRL on the source side of the parallel corpus, cross-lingual model transfer can be performed using only a bilingual dictionary.
    Page 9, “Conclusion”

See all papers in Proc. ACL 2013 that mention parallel data.

See all papers in Proc. ACL that mention parallel data.

Back to top.

dependency parser

Appears in 6 sentences as: dependency parser (4) dependency parsers (1) dependency parsing (1)
In Cross-lingual Transfer of Semantic Role Labeling Models
  1. (2011) successfully apply this idea to the transfer of dependency parsers , using part-of-speech tags as the shared representation of words.
    Page 1, “Background and Motivation”
  2. With respect to the use of syntactic annotation we consider two options: using an existing dependency parser for the target language and obtaining one by means of cross-lingual transfer (see section 4.2).
    Page 2, “Setup”
  3. If a target language is poor in resources, one can obtain a dependency parser for the target language by means of cross-lingual model transfer (Zeman and Resnik, 2008).
    Page 3, “Model Transfer”
  4. In the low-resource setting, we cannot always rely on the availability of an accurate dependency parser for the target language.
    Page 5, “Evaluation”
  5. Secondly, in the model transfer setup it is more important how closely the syntactic-semantic interface on the target side resembles that on the source side than how well it matches the “true” structure of the target language, and in this respect a transferred dependency parser may have an advantage over one trained on target-language data.
    Page 7, “Results”
  6. Cross-lingual annotation projection (Yarowsky et al., 2001) approaches have been applied extensively to a variety of tasks, including POS tagging (Xi and Hwa, 2005; Das and Petrov, 2011), morphology segmentation (Snyder and Barzilay, 2008), verb classification (Merlo et al., 2002), mention detection (Zitouni and Florian, 2008), LFG parsing (Wroblewska and Frank, 2009), information extraction (Kim et al., 2010), SRL (Pado and Lapata, 2009; van der Plas et al., 2011; Annesi and Basili, 2010; Tonelli and Pi-anta, 2008), dependency parsing (Naseem et al., 2012; Ganchev et al., 2009; Smith and Eisner, 2009; Hwa et al., 2005) or temporal relation pre-
    Page 8, “Related Work”

See all papers in Proc. ACL 2013 that mention dependency parser.

See all papers in Proc. ACL that mention dependency parser.

Back to top.

POS tags

Appears in 5 sentences as: POS tagging (1) POS tags (4)
In Cross-lingual Transfer of Semantic Role Labeling Models
  1. This may have a negative effect on the performance of a monolingual model, since most part-of-speech tagsets are more fine-grained than the universal POS tags considered here.
    Page 3, “Model Transfer”
  2. Since the finer-grained POS tags often reflect more language-specific phenomena, however, they would only be useful for very closely related languages in the cross-lingual setting.
    Page 3, “Model Transfer”
  3. If Synt is enabled too, it also uses the POS tags of the argument’s parent, children and siblings.
    Page 4, “Model Transfer”
  4. The part-of-speech tags in all datasets were replaced with the universal POS tags of Petrov et al.
    Page 5, “Evaluation”
  5. Cross-lingual annotation projection (Yarowsky et al., 2001) approaches have been applied extensively to a variety of tasks, including POS tagging (Xi and Hwa, 2005; Das and Petrov, 2011), morphology segmentation (Snyder and Barzilay, 2008), verb classification (Merlo et al., 2002), mention detection (Zitouni and Florian, 2008), LFG parsing (Wroblewska and Frank, 2009), information extraction (Kim et al., 2010), SRL (Pado and Lapata, 2009; van der Plas et al., 2011; Annesi and Basili, 2010; Tonelli and Pi-anta, 2008), dependency parsing (Naseem et al., 2012; Ganchev et al., 2009; Smith and Eisner, 2009; Hwa et al., 2005) or temporal relation pre-
    Page 8, “Related Work”

See all papers in Proc. ACL 2013 that mention POS tags.

See all papers in Proc. ACL that mention POS tags.

Back to top.

manual annotation

Appears in 4 sentences as: manual annotation (3) manually annotated (1)
In Cross-lingual Transfer of Semantic Role Labeling Models
  1. Several approaches have been proposed to obtain an SRL model for a new language with little or no manual annotation .
    Page 2, “Setup”
  2. For English-French, the English CoNLL-ST dataset was used as a source and the model was evaluated on the manually annotated dataset from van der Plas et al.
    Page 5, “Evaluation”
  3. Note that in case of French we evaluate against the output of a supervised system, since manual annotation is not available for this dataset.
    Page 5, “Evaluation”
  4. It allows one to quickly construct an SRL model for a new language without manual annotation or language-specific heuristics, provided an accurate model is available for one of the related languages along with a certain amount of parallel data for the two languages.
    Page 8, “Conclusion”

See all papers in Proc. ACL 2013 that mention manual annotation.

See all papers in Proc. ACL that mention manual annotation.

Back to top.

parallel corpus

Appears in 3 sentences as: parallel corpus (3)
In Cross-lingual Transfer of Semantic Role Labeling Models
  1. The mapping (bilingual dictionary) we use is derived from a word-aligned parallel corpus , by identifying, for each word in the target language,
    Page 3, “Model Transfer”
  2. Projection Baseline: The projection baseline we use for English-Czech and English-Chinese is a straightforward one: we label the source side of a parallel corpus using the source-language model, then identify those verbs on the target side that are aligned to a predicate, mark them as predicates and propagate the argument roles in the same fashion.
    Page 6, “Evaluation”
  3. notation projection approaches require sentence-and word-aligned parallel data and crucially depend on the accuracy of the syntactic parsing and SRL on the source side of the parallel corpus , cross-lingual model transfer can be performed using only a bilingual dictionary.
    Page 9, “Conclusion”

See all papers in Proc. ACL 2013 that mention parallel corpus.

See all papers in Proc. ACL that mention parallel corpus.

Back to top.

word order

Appears in 3 sentences as: Word order (1) word order (2)
In Cross-lingual Transfer of Semantic Role Labeling Models
  1. Word order information constitutes an implicit group that is always available.
    Page 4, “Model Transfer”
  2. may be partly attributed to the fact that the mapping is derived from the same corpus as the evaluation data — Europarl (Koehn, 2005) — and partly by the similarity between English and French in terms of word order , usage of articles and prepositions.
    Page 8, “Results”
  3. This makes it hard to account for phenomena that are expressed differently in the languages considered, for example the syntactic function of a certain word may be indicated by a preposition, inflection or word order , depending on the language.
    Page 8, “Related Work”

See all papers in Proc. ACL 2013 that mention word order.

See all papers in Proc. ACL that mention word order.

Back to top.

PDF available from www.aclweb.org.
Send us an email