Articles

Understanding language goes hand in hand with the ability to integrate complex contextual information obtained via per- ception. In this work, we present a novel task for grounded language understanding: disambiguating a sentence given a visual scene which depicts one of the possible interpretations of that sentence. To this end, …...

This paper introduces GEOS, the first au- tomated system to solve unaltered SAT ge- ometry questions by combining text un- derstanding and diagram interpretation. We model the problem of understanding geometry questions as submodular opti- mization, and identify a formal problem description likely to be compatible with both the question …...

Semantic parsing maps a sentence in natu- ral language into a structured meaning rep- resentation. Previous studies show that se- mantic parsing with synchronous context- free grammars (SCFGs) achieves favor- able performance over most other alter- natives. Motivated by the observation that the performance of semantic pars- ing with SCFGs …...

Joint models of syntactic and semantic parsing have the potential to improve performance on both tasks—but to date, the best results have been achieved with pipelines. We introduce a joint model us- ing CCG, which is motivated by the close link between CCG syntax and semantics. Semantic roles are recovered …...

Online forum discussions proceed differ- ently from face-to-face conversations and any single thread on an online forum con- tains posts on different subtopics. This work aims to characterize the content of a forum thread as a conversation tree of topics. We present models that jointly per- form two tasks: segment …...

An attentional mechanism has lately been used to improve neural machine transla- tion (NMT) by selectively focusing on parts of the source sentence during trans- lation. However, there has been little work exploring useful architectures for attention-based NMT. This paper exam- ines two simple and effective classes of at- tentional …...

We propose a conversion of bilingual sentence pairs and the corresponding word alignments into novel linear se- quences. These are joint translation and reordering (JTR) uniquely defined sequences, combining interdepending lexical and alignment dependencies on the word level into a single framework. They are constructed in a simple manner while …...

The tasks in fine-grained opinion mining can be regarded as either a token-level se- quence labeling problem or as a semantic compositional task. We propose a gen- eral class of discriminative models based on recurrent neural networks (RNNs) and word embeddings that can be successfully applied to such tasks without …...

Document level sentiment classification remains a challenge: encoding the intrin- sic relations between sentences in the se- mantic meaning of a document. To ad- dress this, we introduce a neural network model to learn vector-based document rep- resentation in a unified, bottom-up fash- ion. The model first learns sentence rep- …...

In hierarchical phrase-based translation, coarse-grained nonterminal Xs may gen- erate inappropriate translations due to the lack of sufficient information for phrasal substitution. In this paper we propose a framework to refine nonterminals in hier- archical translation rules with real-valued semantic representations. The semantic representations are learned via a weighted mean …...

The multilingual Paraphrase Database (PPDB) is a freely available automatically created resource of paraphrases in mul- tiple languages. In statistical machine translation, paraphrases can be used to provide translation for out-of-vocabulary (OOV) phrases. In this paper, we show that a graph propagation approach that uses PPDB paraphrases can be used …...

Transition-based dependency parsers usu- ally use transition systems that monotoni- cally extend partial parse states until they identify a complete parse tree. Honni- bal et al. (2013) showed that greedy one- best parsing accuracy can be improved by adding additional non-monotonic tran- sitions that permit the parser to “repair” earlier …...

Model combination techniques have con- sistently shown state-of-the-art perfor- mance across multiple tasks, including syntactic parsing. However, they dramat- ically increase runtime and can be diffi- cult to employ in practice. We demon- strate that applying constituency model combination techniques to n-best lists in- stead of n different parsers results …...

We extend and improve upon recent work in struc- tured training for neural network transition-based dependency parsing. We do this by experimenting with novel features, additional transition systems and by testing on a wider array of languages. In par- ticular, we introduce set-valued features to encode the predicted morphological properties …...

We present a new treebank of English and French technical forum content which has been annotated for grammatical errors and phrase structure. This double annotation allows us to empirically measure the effect of errors on parsing performance. While it is slightly easier to parse the corrected versions of the forum …...

We present a semi-supervised approach to improve dependency parsing accuracy by using bilexical statistics derived from auto-parsed data. The method is based on estimating the attachment potential of head-modifier words, by taking into ac- count not only the head and modifier words themselves, but also the words sur- rounding the …...

We propose online unsupervised domain adaptation (DA), which is performed in- crementally as data comes in and is appli- cable when batch DA is not possible. In a part-of-speech (POS) tagging evaluation, we find that online unsupervised DA per- forms as well as batch DA. 1...

We introduce an extension to the bag-of- words model for learning words represen- tations that take into account both syn- tactic and semantic properties within lan- guage. This is done by employing an at- tention model that finds within the con- textual words, the words that are relevant for each …...

We present an approach to Arabic auto- matic diacritization that integrates syntac- tic analysis with morphological tagging through improving the prediction of case and state features. Our best system in- creases the accuracy of word diacritization by 2.5% absolute on all words, and 5.2% absolute on nominals over a state-of-the- …...

In this paper, we address the challenge of creating accurate and robust part- of-speech taggers for low-resource lan- guages. We propose a method that lever- ages existing parallel data between the tar- get language and a large set of resource- rich languages without ancillary resources such as tag dictionaries. Crucially, …...