Results 1 
7 of
7
A Confidence Model for SyntacticallyMotivated Entailment Proofs
"... This paper presents a novel method for recognizing textual entailment which derives the hypothesis from the text through a sequence of parse tree transformations. Unlike related approaches based on treeeditdistance, we employ transformations which better capture linguistic structures of entailment ..."
Abstract

Cited by 6 (5 self)
 Add to MetaCart
This paper presents a novel method for recognizing textual entailment which derives the hypothesis from the text through a sequence of parse tree transformations. Unlike related approaches based on treeeditdistance, we employ transformations which better capture linguistic structures of entailment. This is achieved by (a) extending an earlier deterministic knowledgebased algorithm with syntacticallymotivated onthefly transformations, and (b) by introducing an algorithm that uniformly learns costs for all types of transformations. Our evaluations and analysis support the validity of this approach. 1
Answer extraction as sequence tagging with tree edit distance
 In North American Chapter of the Association for Computational Linguistics (NAACL
, 2013
"... Our goal is to extract answers from preretrieved sentences for Question Answering (QA). We construct a linearchain Conditional Random Field based on pairs of questions and their possible answer sentences, learning the association between questions and answer types. This casts answer extraction as a ..."
Abstract

Cited by 2 (2 self)
 Add to MetaCart
Our goal is to extract answers from preretrieved sentences for Question Answering (QA). We construct a linearchain Conditional Random Field based on pairs of questions and their possible answer sentences, learning the association between questions and answer types. This casts answer extraction as an answer sequence tagging problem for the first time, where knowledge of shared structure between question and source sentence is incorporated through features based on Tree Edit Distance (TED). Our model is free of manually created question and answer templates, fast to run (processing 200 QA pairs per second excluding parsing time), and yields an F1 of 63.3 % on a new public dataset based on prior TREC QA evaluations. The developed system is opensource, and includes an implementation of the TED model that is state of the art in the task of ranking QA pairs. 1
Probabilistic Finite State Machines for Regressionbased MT Evaluation
"... Accurate and robust metrics for automatic evaluation are key to the development of statistical machine translation (MT) systems. We first introduce a new regression model that uses a probabilistic finite state machine (pFSM) to compute weighted edit distance as predictions of translation quality. We ..."
Abstract
 Add to MetaCart
Accurate and robust metrics for automatic evaluation are key to the development of statistical machine translation (MT) systems. We first introduce a new regression model that uses a probabilistic finite state machine (pFSM) to compute weighted edit distance as predictions of translation quality. We also propose a novel pushdown automaton extension of the pFSM model for modeling word swapping and cross alignments that cannot be captured by standard edit distance models. Our models can easily incorporate a rich set of linguistic features, and automatically learn their weights, eliminating the need for adhoc parameter tuning. Our methods achieve stateoftheart correlation with human judgments on two different prediction tasks across a diverse set of standard evaluations (NIST OpenMT06,08; WMT0608). 1
Efficient Search for Transformationbased Inference
"... This paper addresses the search problem in textual inference, where systems need to infer one piece of text from another. A prominent approach to this task is attempts to transform one text into the other through a sequence of inferencepreserving transformations, a.k.a. a proof, while estimating th ..."
Abstract
 Add to MetaCart
This paper addresses the search problem in textual inference, where systems need to infer one piece of text from another. A prominent approach to this task is attempts to transform one text into the other through a sequence of inferencepreserving transformations, a.k.a. a proof, while estimating the proof’s validity. This raises a search challenge of finding the best possible proof. We explore this challenge through a comprehensive investigation of prominent search algorithms and propose two novel algorithmic components specifically designed for textual inference: a gradientstyle evaluation function, and a locallookahead node expansion method. Evaluations, using the opensource system, BIUTEE, show the contribution of these ideas to search efficiency and proof quality. 1
SemiMarkov Phrasebased Monolingual Alignment
"... We introduce a novel discriminative model for phrasebased monolingual alignment using a semiMarkov CRF. Our model achieves stateoftheart alignment accuracy on two phrasebased alignment datasets (RTE and paraphrase), while doing significantly better than other strong baselines in both nonidentic ..."
Abstract
 Add to MetaCart
We introduce a novel discriminative model for phrasebased monolingual alignment using a semiMarkov CRF. Our model achieves stateoftheart alignment accuracy on two phrasebased alignment datasets (RTE and paraphrase), while doing significantly better than other strong baselines in both nonidentical alignment and phraseonly alignment. Additional experiments highlight the potential benefit of our alignment model to RTE, paraphrase identification and question answering, where even a naive application of our model’s alignment score approaches the state of the art. 1
Learning Semantic Textual Similarity with Structural Representations
"... Measuring semantic textual similarity (STS) is at the cornerstone of many NLP applications. Different from the majority of approaches, where a large number of pairwise similarity features are used to represent a text pair, our model features the following: (i) it directly encodes input texts into re ..."
Abstract
 Add to MetaCart
Measuring semantic textual similarity (STS) is at the cornerstone of many NLP applications. Different from the majority of approaches, where a large number of pairwise similarity features are used to represent a text pair, our model features the following: (i) it directly encodes input texts into relational syntactic structures; (ii) relies on tree kernels to handle feature engineering automatically; (iii) combines both structural and feature vector representations in a single scoring model, i.e., in Support Vector Regression (SVR); and (iv) delivers significant improvement over the best STS systems. 1
Question Answering Using Enhanced Lexical Semantic Models
"... In this paper, we study the answer sentence selection problem for question answering. Unlike previous work, which primarily leverages syntactic analysis through dependency tree matching, we focus on improving the performance using models of lexical semantic resources. Experiments show that our syste ..."
Abstract
 Add to MetaCart
In this paper, we study the answer sentence selection problem for question answering. Unlike previous work, which primarily leverages syntactic analysis through dependency tree matching, we focus on improving the performance using models of lexical semantic resources. Experiments show that our systems can be consistently and significantly improved with rich lexical semantic information, regardless of the choice of learning algorithms. When evaluated on a benchmark dataset, the MAP and MRR scores are increased by 8 to 10 points, compared to one of our baseline systems using only surfaceform matching. Moreover, our best system also outperforms pervious work that makes use of the dependency tree structure by a wide margin. 1