Wen-tau Yih

The importance of syntactic parsing and inference in semantic role labeling

We present a general framework for semantic role labeling. The framework combines a machine-learning technique with an integer linear programming-based inference procedure, which incorporates linguistic and structural constraints into a global decision process. Within this framework, we study the role of syntactic parsing information in semantic role labeling. We show that full syntactic parsing information is, by far, most relevant in identifying the argument, especially, in the very first stagethe pruning stage. Surprisingly, the quality of the pruning stage cannot be solely determined based on its recall and precision. Instead, it depends on the characteristics of the output candidates that determine the difficulty of the downstream problems. Motivated by this observation, we propose an effective and simple approach of combining different semantic role labeling systems through joint inference, which significantly improves its performance. Our system has been evaluated in the CoNLL-2005 shared task on semantic role labeling, and achieves the highest F1 score among 19 participants.

Integer linear programming inference for conditional random fields

Inference in Conditional Random Fields and Hidden Markov Models is done using the Viterbi algorithm, an efficient dynamic programming algorithm. In many cases, general (non-local and non-sequential) constraints may exist over the output sequence, but cannot be incorporated and exploited in a natural way by this inference procedure. This paper proposes a novel inference procedure based on integer linear programming (ILP) and extends CRF models to naturally and efficiently support general constraint structures. For sequential constraints, this procedure reduces to simple linear programming as the inference process. Experimental evidence is supplied in the context of an important NLP problem, semantic role labeling.

Semantic role labeling via integer linear programming inference

We present a system for the semantic role labeling task. The system combines a machine learning technique with an inference procedure based on integer linear programming that supports the incorporation of linguistic and structural constraints into the decision process. The system is tested on the data provided in CoNLL-2004 shared task on semantic role labeling and achieves very competitive results.

Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base

We propose a novel semantic parsing framework for question answering using a knowledge base. We define a query graph that resembles subgraphs of the knowledge base and can be directly mapped to a logical form. Semantic parsing is reduced to query graph generation, formulated as a staged search problem. Unlike traditional approaches, our method leverages the knowledge base in an early stage to prune the search space and thus simplifies the semantic matching problem. By applying an advanced entity linking system and a deep convolutional neural network model that matches questions and predicate sequences, our system outperforms previous methods substantially, and achieves an F1 measure of 52.5% on the WEBQUESTIONS dataset.

Semantic Parsing for Single-Relation Question Answering

We develop a semantic parsing framework based on semantic similarity for open domain question answering (QA). We focus on single-relation questions and decompose each question into an entity mention and a relation pattern. Using convolutional neural network models, we measure the similarity of entity mentions with entities in the knowledge base (KB) and the similarity of relation patterns and relations in the KB. We score relational triples in the KB using these measures and select the top scoring relational triple to answer the question. When evaluated on an open-domain QA task, our method achieves higher precision across different recall points compared to the previous approach, and can improve F1 by 7 points.

WikiQA: A Challenge Dataset for Open-Domain Question Answering

We describe the WIKIQA dataset, a new publicly available set of question and sentence pairs, collected and annotated for research on open-domain question answering. Most previous work on answer sentence selection focuses on a dataset created using the TREC-QA data, which includes editor-generated questions and candidate answer sentences selected by matching content words in the question. WIKIQA is constructed using a more natural process and is more than an order of magnitude larger than the previous dataset. In addition, the WIKIQA dataset also includes questions for which there are no correct sentences, enabling researchers to work on answer triggering, a critical component in any QA system. We compare several systems on the task of answer sentence selection on both datasets and also describe the performance of a system on the problem of answer triggering using the WIKIQA dataset.

Generalized Inference with Multiple Semantic Role Labeling Systems

We present an approach to semantic role labeling (SRL) that takes the output of multiple argument classifiers and combines them into a coherent predicate-argument output by solving an optimization problem. The optimization stage, which is solved via integer linear programming, takes into account both the recommendation of the classifiers and a set of problem specific constraints, and is thus used both to clean the classification results and to ensure structural integrity of the final role labeling. We illustrate a significant improvement in overall SRL performance through this inference.

Typed Tensor Decomposition of Knowledge Bases for Relation Extraction

While relation extraction has traditionally been viewed as a task relying solely on textual data, recent work has shown that by taking as input existing facts in the form of entity-relation triples from both knowledge bases and textual data, the performance of relation extraction can be improved significantly. Following this new paradigm, we propose a tensor decomposition approach for knowledge base embedding that is highly scalable, and is especially suitable for relation extraction. By leveraging relational domain knowledge about entity type information, our learning algorithm is significantly faster than previous approaches and is better able to discover new relations missing from the database. In addition, when applied to a relation extraction task, our approach alone is comparable to several existing systems, and improves the weighted mean average precision of a state-of-theart method by 10 points when used as a subcomponent.

Learning Continuous Phrase Representations for Translation Modeling

This paper tackles the sparsity problem in estimating phrase translation probabilities by learning continuous phrase representations, whose distributed nature enables the sharing of related phrases in their representations. A pair of source and target phrases are projected into continuous-valued vector representations in a low-dimensional latent space, where their translation score is computed by the distance between the pair in this new space. The projection is performed by a neural network whose weights are learned on parallel training data. Experimental evaluation has been performed on two WMT translation tasks. Our best result improves the performance of a state-of-the-art phrase-based statistical machine translation system trained on WMT 2012 French-English data by up to 1.3 BLEU points.

Clickthrough-based latent semantic models for web search

This paper presents two new document ranking models for Web search based upon the methods of semantic representation and the statistical translation-based approach to information retrieval (IR). Assuming that a query is parallel to the titles of the documents clicked on for that query, large amounts of query-title pairs are constructed from clickthrough data; two latent semantic models are learned from this data. One is a bilingual topic model within the language modeling framework. It ranks documents for a query by the likelihood of the query being a semantics-based translation of the documents. The semantic representation is language independent and learned from query-title pairs, with the assumption that a query and its paired titles share the same distribution over semantic topics. The other is a discriminative projection model within the vector space modeling framework. Unlike Latent Semantic Analysis and its variants, the projection matrix in our model, which is used to map from term vectors into sematic space, is learned discriminatively such that the distance between a query and its paired title, both represented as vectors in the projected semantic space, is smaller than that between the query and the titles of other documents which have no clicks for that query. These models are evaluated on the Web search task using a real world data set. Results show that they significantly outperform their corresponding baseline models, which are state-of-the-art.