In contrast, alignment based methods used word alignment model to fulfill this task, which could avoid parsing errors without using parsing.

We further combine syntactic patterns with alignment model by using a partially supervised framework and investigate whether this combination is useful or not.

Nevertheless, we notice that the alignment model is a statistical model which needs sufficient data to estimate parameters.

To answer these questions, in this paper, we adopt a unified framework to extract opinion targets from reviews, in the key component of which we vary the methods between syntactic patterns and alignment model .

Furthermore, this paper naturally addresses another question: is it useful for opinion targets extraction when we combine syntactic patterns and word alignment model into a unified model?

In the first component, we respectively use syntactic patterns and unsupervised word alignment model (WAM) to capture opinion relations.

In addition, we employ a partially supervised word alignment model (PSWAM) to incorporate syntactic information into WAM.

3.1.2 Unsupervised Word Alignment Model

(Liu et al., 2013) extend Liu’s method, which is similar to our method and also used a partially supervised alignment model to extract opinion targets from reviews.

Complementing this model, we build an alignment model (P(a|ws,wt,7rs,7rt)) that scores alignments a given the source and target sentences and their predicted reorderings according to source and target reordering models.

The model (C(773|ws, wt, a)) helps to produce better reference reorderings for training our final reordering model given fixed machine alignments and the alignment model (P (a|ws, Wt, 773, 79)) helps improve the machine alignments taking into account information from reordering models.

St 2: Feed predictions the reordering models to the alignment model

We observe that NER label information can be used to correct alignment mistakes, and present a graphical model that performs bilingual NER tagging jointly with word alignment, by combining two monolingual tagging models with two unidirectional alignment models .

directional HMM models as our baseline and monolingual alignment models .

To capture this source of information, we present a novel extension that combines the BI-NER model with two unidirectional HMM-based alignment models , and perform joint decoding of NER and word alignments.

The new model (denoted as BI-NER-WA) factors over five components: one NER model and one word alignment model for each language, plus a joint NER-alignment model which not only enforces NER label agreements but also facilitates message passing among the other four components.

Most commonly used alignment models , such as the IBM models and HMM-based aligner are unsupervised learners, and can only capture simple distortion features and lexical translational features due to the high complexity of the structure prediction space.

We name the Chinese-to-English aligner model as m(Be) and the reverse directional model 71(Bf Be is a matrix that holds the output of the Chinese-to-English aligner.

In our experiments, we used two HMM-based alignment models .

We describe in detail how we adapt and extend the CD-DNN-HMM (Dahl et al., 2012) method introduced in speech recognition to the HMM-based word alignment model , in which bilingual word embedding is discrimina-tively learnt to capture lexical translation information, and surrounding words are leveraged to model context information in bilingual sentences.

Secondly, we want to explore the possibility of unsupervised training of our neural word alignment model , without reliance of alignment result of other models.

Our DNN word alignment model extends classic HMM word alignment model (Vogel et al., 1996).

In the classic HMM word alignment model , context is not considered in the lexical translation probability.

Vocabulary V of our alignment model consists of a source vocabulary V6 and a target vocabulary Vf.

In future we would like to explore whether our method can improve other word alignment models .

embeddings trained by our word alignment model .

As we do not have a large manually word aligned corpus, we use traditional word alignment models such as HMM and IBM model 4 to generate word alignment on a large parallel corpus.

Tunable parameters in neural network alignment model include: word embeddings in lookup table LT, parameters Wl, bl for linear transformations in the hidden layers of the neural network, and distortion parameters 3d of jump distance.

The number of parallel messages is estimated by running our alignment model , and checking if 7' > gb, where gb was set empirically initially, and optimized after obtaining annotated data, which will be detailed in 5.1.

Finally, we run our alignment model described in section 3, and obtain the parallel segments and their scores, which measure how likely those segments are parallel.

Then, we would use an word alignment model (Brown et al., 1993; Vogel et al., 1996), with source s = sup, .

Firstly, word alignment models generally attribute higher probabilities to smaller segments, since these are the result of a smaller product chain of probabilities.

This may suggest that adding shallow semantic information is more effective than introducing complex structured constraints, at least for the specific word alignment model we experimented with in this work.

Compared to the previous work, our latent alignment model improves the result on a benchmark dataset by a wide margin — the mean average precision (MAP) and mean reciprocal rank (MRR) scores are increased by 25.6% and 18.8%, respectively.

Second, while the latent alignment model performs better than unstructured models, the difference diminishes after adding the enhanced lexical semantics information.

This may suggest that compared to introducing complex structured constraints, incorporating shallow semantic information is both more effective and computationally inexpensive in improving the performance, at least for the specific word alignment model tested in this work.