Natural language sentence matching is a fundamental technology for a variety of tasks. Previous approaches either match sentences from a single direction or only apply single granular (wordby-word or sentence-by-sentence) matching. In this work, we propose a bilateral multi-perspective matching (BiMPM) model. Given two sentences P and Q, our model first encodes them with a BiL-STM encoder. Next, we match the two encoded sentences in two directions P against Q and Q against P . In each matching direction, each time step of one sentence is matched against all timesteps of the other sentence from multiple perspectives. Then, another BiLSTM layer is utilized to aggregate the matching results into a fixed-length matching vector. Finally, based on the matching vector, a decision is made through a fully connected layer. We evaluate our model on three tasks: paraphrase identification, natural language inference and answer sentence selection. Experimental results on standard benchmark datasets show that our model achieves the state-of-the-art performance on all tasks.

This paper presents a classifier-combination experimental framework for named entity recognition in which four diverse classifiers (robust linear classifier, maximum entropy, transformation-based learning, and hidden Markov model) are combined under different conditions. When no gazetteer or other additional training resources are used, the combined system attains a performance of 91.6F on the English development data; integrating name, location and person gazetteers, and named entity systems trained on additional, more general, data reduces the F-measure error by a factor of 15 to 21% on the English data.

The state-of-the-art named entity recognition (NER) systems are supervised machine learning models that require large amounts of manually annotated data to achieve high accuracy. However, annotating NER data by human is expensive and time-consuming, and can be quite difficult for a new language. In this paper, we present two weakly supervised approaches for cross-lingual NER with no human annotation in a target language. The first approach is to create automatically labeled NER data for a target language via annotation projection on comparable corpora, where we develop a heuristic scheme that effectively selects goodquality projection-labeled data from noisy data. The second approach is to project distributed representations of words (word embeddings) from a target language to a source language, so that the sourcelanguage NER system can be applied to the target language without re-training. We also design two co-decoding schemes that effectively combine the outputs of the two projection-based approaches. We evaluate the performance of the proposed approaches on both in-house and open NER data for several target languages. The results show that the combined systems outperform three other weakly supervised approaches on the CoNLL data.

Entity detection and tracking is a relatively new addition to the repertoire of natural language tasks. In this paper, we present a statistical language-independent framework for identifying and tracking named, nominal and pronominal references to entities within unrestricted text documents, and chaining them into clusters corresponding to each logical entity present in the text. Both the mention detection model and the novel entity tracking model can use arbitrary feature types, being able to integrate a wide array of lexical, syntactic and semantic features. In addition, the mention detection model crucially uses feature streams derived from different named entity classifiers. The proposed framework is evaluated with several experiments run in Arabic, Chinese and English texts; a system based on the approach described here and submitted to the latest Automatic Content Extraction (ACE) evaluation achieved top-tier results in all three evaluation languages.

Meaning Representations (AMRs) are broad-coverage sentence-level semantic graphs. Existing approaches to generating text from AMR have focused on training sequenceto-sequence or graph-to-sequence models on AMR annotated data only. In this paper, we propose an alternative approach that combines a strong pre-trained language model with cycle consistency-based re-scoring. Despite the simplicity of the approach, our experimental results show these models outperform all previous techniques on the English LDC2017T10 dataset, including the recent use of transformer architectures. In addition to the standard evaluation metrics, we provide human evaluation experiments that further substantiate the strength of our approach.

Multi-hop reading comprehension focuses on one type of factoid question, where a system needs to properly integrate multiple pieces of evidence to correctly answer a question. Previous work approximates global evidence with local coreference information, encoding coreference chains with DAG-styled GRU layers within a gated-attention reader. However, coreference is limited in providing information for rich inference. We introduce a new method for better connecting global evidence, which forms more complex graphs compared to DAGs. To perform evidence integration on our graphs, we investigate two recent graph neural networks, namely graph convolutional network (GCN) and graph recurrent network (GRN). Experiments on two standard datasets show that richer global information leads to better answers. Our method performs better than all published results on these datasets.

This paper presents a comprehensive empirical exploration and evaluation of a diverse range of data characteristics which influence word sense disambiguation performance. It focuses on a set of six core supervised algorithms, including three variants of Bayesian classifiers, a cosine model, non-hierarchical decision lists, and an extension of the transformation-based learning model. Performance is investigated in detail with respect to the following parameters: (a) target language (English, Spanish, Swedish and Basque); (b) part of speech; (c) sense granularity; (d) inclusion and exclusion of major feature classes; (e) variable context width (further broken down by part-of-speech of keyword); (f) number of training examples; (g) baseline probability of the most likely sense; (h) sense distributional entropy; (i) number of senses per keyword; (j) divergence between training and test data; (k) degree of (artificially introduced) noise in the training data; (l) the effectiveness of an algorithm's confidence rankings; and (m) a full keyword breakdown of the performance of each algorithm. The paper concludes with a brief analysis of similarities, differences, strengths and weaknesses of the algorithms and a hierarchical clustering of these algorithms based on agreement of sense classification behavior. Collectively, the paper constitutes the most comprehensive survey of evaluation measures and tests yet applied to sense disambiguation algorithms. And it does so over a diverse range of supervised algorithms, languages and parameter spaces in single unified experimental framework.

No abstract