Wei Xu

Bio: Wei Xu is an academic researcher from Georgia Institute of Technology. The author has contributed to research in topics: Relationship extraction & Named-entity recognition. The author has an hindex of 23, co-authored 75 publications receiving 2447 citations. Previous affiliations of Wei Xu include Hong Kong Polytechnic University & New York University.

Optimizing Statistical Machine Translation for Text Simplification

Abstract: Most recent sentence simplification systems use basic machine translation models to learn lexical and syntactic paraphrases from a manually simplified parallel corpus. These methods are limited by the quality and quantity of manually simplified corpora, which are expensive to build. In this paper, we conduct an in-depth adaptation of statistical machine translation to perform text simplification, taking advantage of large-scale paraphrases learned from bilingual texts and a small amount of manual simplifications with multiple references. Our work is the first to design automatic metrics that are effective for tuning and evaluating simplification systems, which will facilitate iterative development for this task.

Problems in Current Text Simplification Research: New Data Can Help

Abstract: Simple Wikipedia has dominated simplification research in the past 5 years. In this opinion paper, we argue that focusing on Wikipedia limits simplification research. We back up our arguments with corpus analysis and by highlighting statements that other researchers have made in the simplification literature. We introduce a new simplification dataset that is a significant improvement over Simple Wikipedia, and present a novel quantitative-comparative approach to study the quality of simplification data resources.

Shared Tasks of the 2015 Workshop on Noisy User-generated Text: Twitter Lexical Normalization and Named Entity Recognition

Abstract: This paper presents the results of the two shared tasks associated with W-NUT 2015: (1) a text normalization task with 10 participants; and (2) a named entity tagging task with 8 participants. We outline the task, annotation process and dataset statistics, and provide a high-level overview of the participating systems for each shared task.

SemEval-2015 Task 1: Paraphrase and Semantic Similarity in Twitter (PIT)

Abstract: In this shared task, we present evaluations on two related tasks Paraphrase Identification (PI) and Semantic Textual Similarity (SS) systems for the Twitter data. Given a pair of sentences, participants are asked to produce a binary yes/no judgement or a graded score to measure their semantic equivalence. The task features a newly constructed Twitter Paraphrase Corpus that contains 18,762 sentence pairs. A total of 19 teams participated, submitting 36 runs to the PI task and 26 runs to the SS task. The evaluation shows encouraging results and open challenges for future research. The best systems scored a F1-measure of 0.674 for the PI task and a Pearson correlation of 0.619 for the SS task respectively, comparing to a strong baseline using logistic regression model of 0.589 F1 and 0.511 Pearson; while the best SS systems can often reach >0.80 Pearson on well-formed text. This shared task also provides insights into the relation between the PI and SS tasks and suggests the importance to bringing these two research areas together. We make all the data, baseline systems and evaluation scripts publicly available. 1

Paraphrasing for Style

Abstract: We present initial investigation into the task of paraphrasing language while targeting a particular writing style. The plays of William Shakespeare and their modern translations are used as a testbed for evaluating paraphrase systems targeting a specific style of writing. We show that even with a relatively small amount of parallel training data, it is possible to learn paraphrase models which capture stylistic phenomena, and these models outperform baselines based on dictionaries and out-of-domain parallel text. In addition we present an initial investigation into automatic evaluation metrics for paraphrasing writing style. To the best of our knowledge this is the first work to investigate the task of paraphrasing text with the goal of targeting a specific style of writing.

SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation

Abstract: Semantic Textual Similarity (STS) measures the meaning similarity of sentences. Applications include machine translation (MT), summarization, generation, question answering (QA), short answer grading, semantic search, dialog and conversational systems. The STS shared task is a venue for assessing the current state-of-the-art. The 2017 task focuses on multilingual and cross-lingual pairs with one sub-track exploring MT quality estimation (MTQE) data. The task obtained strong participation from 31 teams, with 17 participating in all language tracks. We summarize performance and review a selection of well performing methods. Analysis highlights common errors, providing insight into the limitations of existing models. To support ongoing work on semantic representations, the STS Benchmark is introduced as a new shared training and evaluation set carefully selected from the corpus of English STS shared task data (2012-2017).

Im2Text: Describing Images Using 1 Million Captioned Photographs

Abstract: We develop and demonstrate automatic image description methods using a large captioned photo collection. One contribution is our technique for the automatic collection of this new dataset – performing a huge number of Flickr queries and then filtering the noisy results down to 1 million images with associated visually relevant captions. Such a collection allows us to approach the extremely challenging problem of description generation using relatively simple non-parametric methods and produces surprisingly effective results. We also develop methods incorporating many state of the art, but fairly noisy, estimates of image content to produce even more pleasing results. Finally we introduce a new objective performance measure for image captioning.

SemEval-2017 Task 1: Semantic Textual Similarity Multilingual and Crosslingual Focused Evaluation

Abstract: Semantic Textual Similarity (STS) measures the meaning similarity of sentences. Applications include machine translation (MT), summarization, generation, question answering (QA), short answer grading, semantic search, dialog and conversational systems. The STS shared task is a venue for assessing the current state-of-the-art. The 2017 task focuses on multilingual and cross-lingual pairs with one sub-track exploring MT quality estimation (MTQE) data. The task obtained strong participation from 31 teams, with 17 participating in all language tracks. We summarize performance and review a selection of well performing methods. Analysis highlights common errors, providing insight into the limitations of existing models. To support ongoing work on semantic representations, the STS Benchmark is introduced as a new shared training and evaluation set carefully selected from the corpus of English STS shared task data (2012-2017).

Multi-instance Multi-label Learning for Relation Extraction

Abstract: Distant supervision for relation extraction (RE) -- gathering training data by aligning a database of facts with text -- is an efficient approach to scale RE to thousands of different relations. However, this introduces a challenging learning scenario where the relation expressed by a pair of entities found in a sentence is unknown. For example, a sentence containing Balzac and France may express BornIn or Died, an unknown relation, or no relation at all. Because of this, traditional supervised learning, which assumes that each example is explicitly mapped to a label, is not appropriate. We propose a novel approach to multi-instance multi-label learning for RE, which jointly models all the instances of a pair of entities in text and all their labels using a graphical model with latent variables. Our model performs competitively on two difficult domains.

Leveraging Linguistic Structure For Open Domain Information Extraction

Abstract: Relation triples produced by open domain information extraction (open IE) systems are useful for question answering, inference, and other IE tasks. Traditionally these are extracted using a large set of patterns; however, this approach is brittle on out-of-domain text and long-range dependencies, and gives no insight into the substructure of the arguments. We replace this large pattern set with a few patterns for canonically structured sentences, and shift the focus to a classifier which learns to extract self-contained clauses from longer sentences. We then run natural logic inference over these short clauses to determine the maximally specific arguments for each candidate triple. We show that our approach outperforms a state-of-the-art open IE system on the end-to-end TAC-KBP 2013 Slot Filling task.