Abstract | Techniques that compare short text segments using dependency paths (or simply, paths) appear in a wide range of automated language processing applications including question answering (QA). |
Abstract | In this paper, we introduce a flexible notion of paths that describe chains of words on a dependency path . |
Introduction | Dependency paths (or simply, paths) are compared using techniques such as tree edit distance (Punyakanok et al., 2004; Heilman and Smith, 2010), relation probability (Gao et al., 2004) and parse tree alignment (Wang et al., 2007; Park et al., 2011). |
Introduction | Much work on sentence similarity using dependency paths focuses on question answering (QA) where textual inference requires attention to linguistic detail. |
Introduction | In this paper, we explore a flexible application of dependency paths that overcomes this difficulty. |
Related work | Techniques that compare short text segments using dependency paths are applied to a wide range of automated language processing tasks, including paraphrasing, summarization, entailment detection, QA, machine translation and the evaluation of word, phrase and sentence similarity. |
Related work | A generic approach uses a matching function to compare a dependency path between any two stemmed terms cc and y in a sentence A with any dependency path between cc and y in sentence B. |
Related work | The match score for A and B is computed over all dependency paths in A. |
Argument Identification | o dependency path between a’s head and the predicate |
Argument Identification | o the set of dependency labels of the predicate’s children 0 dependency path conjoined with the POS tag of a’s head |
Argument Identification | 0 dependency path conjoined with the word cluster of a’s head |
Frame Identification with Embeddings | second example, for the predicate run, the agent The athlete is not a direct dependent, but is connected via a longer dependency path . |
Frame Identification with Embeddings | Dependency Paths To capture more relevant context, we developed a second context function as follows. |
Frame Identification with Embeddings | We scanned the training data for a given task (either the PropBank or the FrameNet domains) for the dependency paths that connected the gold predicates to the gold semantic arguments. |
Discussion | Sentences like this have very long (and thus rare) lexical features, but relatively short dependency paths . |
Features | For each sentence we extract a dependency path between each pair of entities. |
Features | A dependency path consists of a series of dependencies, directions and words/chunks representing a traversal of the parse. |
Features | Part-of-speech tags are not included in the dependency path . |
Conclusion | WOE can run in two modes: a CRF extractor (WOEPOS) trained with shallow features like POS tags; a pattern classfier (WOEparse) learned from dependency path patterns. |
Introduction | We show that abstract dependency paths are a highly informative feature when performing unlexicalized extraction. |
Related Work | (Snow et al., 2005) utilize WordNet to learn dependency path patterns for extracting the hypernym relation from text. |
Related Work | However, our results imply that abstracted dependency path features are highly informative for open IE. |
Wikipedia-based Open IE | WOEparse uses a pattern learner to classify whether the shortest dependency path between two noun phrases indicates a semantic relation. |
Wikipedia-based Open IE | Despite some evidence that parser-based features have limited utility in IE (Jiang and Zhai, 2007), we hoped dependency paths would improve precision on long sentences. |
Wikipedia-based Open IE | Shortest Dependency Path as Relation: Unless otherwise noted, WOE uses the Stanford Parser to create dependencies in the “collapsedDepen-dency” format. |
Experiments | We extract dependency paths for each pair of named entities in one sentence. |
Experiments | for words on the dependency paths . |
Experiments | Each entity pair tun and the dependency path which connects them form wit a tuple. |
Introduction | Such patterns could be sequences of lemmas and Part-of-Speech tags, or lexicalized dependency paths . |
Introduction | Whether we use sequences or dependency paths , we will encounter the problem of polysemy. |
Introduction | We perform experiments on New York Times articles and consider lexicalized dependency paths as patterns in our data. |
Related Work | Both DIRT and our approach represent dependency paths using their arguments. |
Data | where s and 7“ denote “source” and “receiver” arguments, which are political actor entities in a predefined set 5, t is a timestep (i.e., a 7-day period) derived from the article’s published date, and wpredpath is a textual predicate expressed as a dependency path that typically includes a verb (we use the terms “predicate-pat ” and “verb-pat ” interchangeably). |
Data | Verb paths are identified by looking at the shortest dependency path between two mentions in a sentence. |
Experiments | Many of our dependency paths, when traversed from the source to receiver direction, also follow surface order, due to English’s SVO word order.6 Therefore we convert each path to a word sequence and match against the TABARI lexicon—plus a few modifications for differences in infinitives and stemming—and find 528 dependency path matches. |
Experiments | We also create a baseline El-regularized logistic regression that uses normalized dependency path counts as the features (10,457 features). |
Model | o For each frame k, draw a multinomial distribution of dependency paths, gbk; N Dir(b / V) (where V is the number of dependency path types). |
Model | The vanilla model is capable of inducing frames through dependency path co-occurences, when multiple events occur in a given context. |
Evaluation Methodology | Figure 5: Dependency path |
Evaluation Methodology | From this dependency tree, we can extract a dependency path shown in Figure 5, which appears to be a strong clue in knowing that these proteins are mentioned as interacting. |
Evaluation Methodology | Figure 6: Tree representation of a dependency path |
Identifying Key Medical Relations | The similarity of two sentences is defined as the bag-of-words similarity of the dependency paths connecting arguments. |
Relation Extraction with Manifold Models | o (3) Syntactic features representing the dependency path between two arguments, such as “subj”, “pred”, “modJiprep” and “objprep” (between arguments “antibiotic” and “lyme disease”) in Figure 2. |
Relation Extraction with Manifold Models | 0 (5) Topic features modeling the words in the dependency path . |
Relation Extraction with Manifold Models | In the example given in Figure 2, the dependency path contains the following words: “be”, “standard therapy” and “for”. |
A Sentence Trimmer with CRFs | We begin by locating terminal nodes, i.e., those which have no incoming edges, depicted as filled circles in Figure 3, and find a dependency (singly linked) path from each terminal node to the root, or a node labeled ‘E’ here, which would give us two paths p1 = ACDE and p2 = BCDE (call them terminating dependency paths , or TDPs). |
Introduction | Later in the paper, we will introduce an approach called the ‘Dependency Path Model’ (DPM) from the previous literature (Section 4), which purports to provide a robust framework for sentence compres- |
The Dependency Path Model | In what follows, we will describe somewhat in detail a prior approach to sentence compression in Japanese which we call the ”dependency path model,” or DPM. |
The Dependency Path Model | Dependency path length (DL) refers to the number of (singly linked) dependency relations (or edges) that span two bunsetsa’s. |
Pattern Combination Method for Relation Extraction | We define dependency patterns as sub-paths of the shortest dependency path between a concept pair for two reasons. |
Pattern Combination Method for Relation Extraction | Shortest dependency path inducement. |
Pattern Combination Method for Relation Extraction | From the original dependency tree structure by parsing the selected sentence for each concept pair, we first induce the shortest dependency path with the entitled concept and related concept. |
Experiments and results | Two ways of extracting patterns have been used: (a) Syntactic, taking the dependency path between the two entities, and (b) Intertext, taking the text between the two. |
Unsupervised relational pattern learning | This context may be a complex structure, such as the dependency path joining the two entities, but it is considered for our purposes as a single term; (e) for each relation r relating 67; with 63-, document Dij is added to collection CT. |
Unsupervised relational pattern learning | The words in each document can be, for example, all the dependency paths that have been observed in the input textual corpus between the two related entities. |
Unsupervised relational pattern learning | Generative model Once these collections are built, we use the generative model from Figure 2 to learn the probability that a dependency path is conveying some relation between the entities it connects. |
Approaches | (2009), we include the notion of verb and noun supports and sections of the dependency path . |
Experiments | This highlights an important advantage of the pipeline trained model: the features can consider any part of the syntax (e. g., arbitrary sub-trees), whereas the joint model is limited to those features over which it can efficiently marginalize (e.g., short dependency paths ). |
Introduction | Even at the expense of no dependency path features, the joint models best pipeline-trained models for state-of-the-art performance in the low-resource setting (§ 4.4). |
Related Work | (2009), who utilize features on syntactic siblings and the dependency path concatenated with the direction of each edge. |
Experiments | We therefore mapped the DIRT Inference rules (Lin and Pantel, 2001), (which consist of pairs of dependency paths ) to TEXTRUNNER relations as follows. |
Experiments | From the parses we extracted all dependency paths between nouns that contain only words present in the TEXTRUNNER relation string. |
Experiments | These dependency paths were then matched against each pair in the DIRT database, and all pairs of associated relations were collected producing about 26,000 inference rules. |
Guided DS | entity types, a dependency path and maybe a span word, if g has one. |
The Challenge | Each guideline g={gi|i=1,2,3} consists of a pair of semantic types, a dependency path , and optionally a span word and is associated with a particular relation r(g). |
The Challenge | Table 3: Performance of a MaxEnt, trained on hand-labeled data using all features (Surdeanu et al., 2011) vs using a subset of two (types of entities, dependency path ), or three (adding a span word) features, and evaluated on the test set. |
Approach | The syntactic rules correspond to the shortest dependency paths between an opinion word and an extracted mention. |
Approach | We consider the 10 most frequent dependency paths in the training data. |
Approach | Example dependency paths include nsubj(opinion, mention), nobj(opinion, mention), and am0d(mention, opinion). |