Articles

Tense prediction can be useful for many language processing tasks, such as tem- poral inference and machine translation. In this paper, we investigate using diverse contextual features for Chinese tense pre- diction under a statistical learning frame- work. Because of lack of annotated train- ing data, we propose to leverage …...

In this paper, we propose a keyword-based passage retrieval algorithm for information ex- traction, trained by distant supervision. Our goal is to be able to extract attributes of people and organizations more quickly and accurately by first ranking all the potentially relevant passages according to their likelihood of con- taining …...

In this paper, we propose a novel context inference-based approach for sentences ordering in multi-document summarization application. Our method first detects whether or not two summarization sentences should be adjacent according to the similarity between one summarization sentence and the context of the other one, and then it computes the …...

We present a novel relevance feedback (RF) method that uses not only the sur- face information in texts, but also the la- tent information contained therein. In the proposed method, we infer the latent topic distribution in user feedback and in each document in the search results using latent Dirichlet …...

This paper proposes a method for automat- ically acquiring strongly-related events from a large corpus using predicate- argument co-occurring statistics and case frames. The strongly-related events are acquired in the form of strongly-related two predicates with their relevant ar- guments. First, strongly-related events are acquired from predicate-argument co- occurring statistics. …...

In this paper, we formalize the task of finding a knowledge base entry that a giv- en named entity mention refers to, name- ly entity linking, by identifying the most “important” node among the graph n- odes representing the candidate entries. With the aim of ranking these entities by their …...

This paper addresses the problem of re- lated entity extraction and focuses on ex- tracting related persons as a case study. The proposed method builds on a search engine. Specifically, we mine candidate related persons for a query person q us- ing q’s search results and the query logs containing …...

This paper addresses the issue of re- dundant data in large-scale collections of Q&A forums. We propose and evaluate a novel algorithm for auto- matically detecting the near-duplicate Q&A threads. The main idea is to use the distributed index and Map- Reduce framework to calculate pair- wise similarity and identify …...

Recent years have seen an exponential growth in the amount of multilingual text available on the web. This situation raises the need for novel applications for or- ganizing and accessing multilingual con- tent. Common examples of such applica- tions include Multilingual Topic Tracking, Cross-Language Information retrieval sys- tems etc. Most …...

This paper describes a two-phase method for expanding abbreviations found in in- formal text (e.g., email, text messages, chat room conversations) using a machine translation system trained at the charac- ter level during the first phase. In this way, the system learns mappings between character-level “phrases” and is much more …...

In this paper we address the problem of obtaining structured information about products in the form of attribute-value pairs by leveraging a combination of enter- prise internal product descriptions and ex- ternal data. Product descriptions are short text strings used internally within enter- prises to describe a product. These strings …...

This paper describes efforts of NLP re- searchers to create a system to aid the relief efforts during the 2011 East Japan Earthquake. Specifically, we created a system to mine information regarding the safety of people in the disaster-stricken area from Twitter, a massive yet highly unorganized information source. We …...

This paper regards social Q&A collec- tions, such as Yahoo! Answer as a knowl- edge repository and investigates tech- niques to mine knowledge from them for improving a sentence-based complex question answering (QA) system. In par- ticular, we present a question-type-specific method (QTSM) that studies at extract- ing question-type-dependent cue …...

Garbage in and garbage out. A Q&A sys- tem must receive a well formulated ques- tion that matches the user’s intent or she has no chance to receive satisfactory an- swers. In this paper, we propose a key- words to questions (K2Q) system to assist a user to articulate and …...

Question classification is a crucial preprocessing for question answering system; it can help to make sure the user’s intention. Most of previous researches fo- cus on the feature driven methods that represent a question with a bag of features, which ignore the im- portant information contained in the words order …...

Community-based Question Answering services contain many threads consisting of a question and its answers. When there are many answers for a question, it is hard for a user to understand them all. To address this problem, we focus on logi- cal relations between answers in a thread and present a …...

This paper proposes a method that auto- matically generates questions from queries for community-based question answering (cQA) services. Our query-to-question generation model is built upon templates induced from search engine query logs. In detail, we first extract pairs of queries and user-clicked questions from query logs, with which we induce …...

Although some multiword expressions (MWEs) like How do you do? have ex- clusively idiomatic meaning, other MWE- types like the phrase kick the bucket may be idiomatic or literal depending on con- text. The recently developed OpenMWE corpus provides the largest freely avail- able collection of annotated MWE-tokens suitable for …...

Recent advances in automatic knowledge acquisition methods have enabled us to construct massive knowledge bases of se- mantic relations. Most previous work has focused on semantic relations explicitly expressed in single sentences. Our goal in this work is to obtain valid non-single sentence relation instances, which are not written in …...

By today, no lexical resource can claim to be fully comprehensive or perform best for every NLP task. This caused a steep increase of resource alignment research. An important challenge is thereby the alignment of differently represented word senses, which we address in this paper. In particular, we propose a …...