Articles

The interpretation of adjective-noun pairs plays a crucial role in tasks such as rec- ognizing textual entailment. Formal se- mantics often places adjectives into a taxonomy which should dictate adjec- tives’ entailment behavior when placed in adjective-noun compounds. However, we show experimentally that the behavior of subsective adjectives (e.g. red) …...

We describe a new technique for improv- ing statistical machine translation training by adopting scores from a recent crosslin- gual semantic frame based evaluation met- ric, XMEANT, as outside probabilities in expectation-maximization based ITG (inversion transduction grammars) align- ment. Our new approach strongly biases early-stage SMT learning towards seman- tically …...

Reasoning over several premises is not a common feature of RTE systems as it usually requires deep semantic analysis. On the other hand, FraCaS is a collec- tion of entailment problems consisting of multiple premises and covering semanti- cally challenging phenomena. We employ the tableau theorem prover for natural lan- …...

It is generally believed that a metaphor tends to have a stronger emotional im- pact than a literal statement; however, there is no quantitative study establishing the extent to which this is true. Further, the mechanisms through which metaphors convey emotions are not well understood. We present the first data-driven …...

This paper presents a rule-based approach to constructing lexical axioms from Word- Net verb entries in an expressive semantic representation, Episodic Logic (EL). EL differs from other representations in be- ing syntactically close to natural language and covering phenomena such as general- ized quantification, modification, and in- tensionality while still …...

Extending semantic role labeling (SRL) to detect and recover non-local arguments continues to be a challenge. Our work is the first to address the detection of im- plicit roles from a multilingual perspec- tive. We map predicate-argument struc- tures across English and German sen- tences, and we develop a classifier …...

The automatic prediction of aspectual classes is very challenging for verbs whose aspectual value varies across readings, which are the rule rather than the excep- tion. This paper sheds a new perspective on this problem by using a machine learn- ing approach and a rich morpho-syntactic and semantic valency lexicon. …...

Do distributional word representations en- code the linguistic regularities that theo- ries of meaning argue they should encode? We address this question in the case of the logical properties (monotonicity, force) of quantificational words such as everything (in the object domain) and always (in the time domain). Using the vector …...

This paper presents the first study using neu- ral machine translation (NMT) for grammati- cal error correction (GEC). We propose a two- step approach to handle the rare word problem in NMT, which has been proved to be useful and effective for the GEC task. Our best NMT- based system …...

Financial news contains useful information on public companies and the market. In this pa- per we apply the popular word embedding methods and deep neural networks to lever- age financial news to predict stock price move- ments in the market. Experimental results have shown that our proposed methods are simple …...

Idioms pose a great challenge to natural lan- guage understanding. A system that can auto- matically paraphrase idioms in context has ap- plications in many NLP tasks. This paper pro- poses a phrasal substitution method to replace idioms with their figurative meanings in literal English. Our approach identifies relevant re- …...

This paper provides a binary, token-based classification of German particle verbs (PVs) into literal vs. non-literal usage. A random forest improving standard features (e.g., bag- of-words; affective ratings) with PV-specific information and abstraction over common nouns significantly outperforms the major- ity baseline. In addition, PV-specific classifi- cation experiments demonstrate the …...

This paper presents a data-driven investiga- tion of phonesthemes, phonetic units said to carry meaning associations, thus challenging the traditionally assumed arbitrariness of lan- guage. Phonesthemes have received a subs- tantial amount of attention within the cogni- tive science literature on sound iconicity, but nevertheless remain a controversial and un- …...

Recurrent Neural Networks (RNNs) have ob- tained excellent result in many natural lan- guage processing (NLP) tasks. However, un- derstanding and interpreting the source of this success remains a challenge. In this paper, we propose Recurrent Memory Network (RMN), a novel RNN architecture, that not only am- plifies the power …...

This paper presents a novel latent variable re- current neural network architecture for jointly modeling sequences of words and (possibly latent) discourse relations between adjacent sentences. A recurrent neural network gen- erates individual words, thus reaping the ben- efits of discriminatively-trained vector repre- sentations. The discourse relations are rep- resented …...

Long Short-Term Memory (LSTM) networks, a type of recurrent neural network with a more complex computational unit, have been successfully applied to a variety of sequence modeling tasks. In this paper we develop Tree Long Short-Term Memory (TREELSTM), a neural network model based on LSTM, which is designed to predict …...

Event extraction is a particularly challenging problem in information extraction. The state- of-the-art models for this problem have ei- ther applied convolutional neural networks in a pipelined framework (Chen et al., 2015) or followed the joint architecture via structured prediction with rich local and global features (Li et al., 2013). …...

Events and entities are closely related; entities are often actors or participants in events and events without entities are uncommon. The interpretation of events and entities is highly contextually dependent. Existing work in in- formation extraction typically models events separately from entities, and performs infer- ence at the sentence level, …...

In named entity recognition task especially for massive data like Twitter, having a large amount of high quality gazetteers can allevi- ate the problem of training data scarcity. One could collect large gazetteers from knowl- edge graph and phrase embeddings to obtain high coverage of gazetteers. However, large gazetteers cause …...

State-of-the-art named entity recognition sys- tems rely heavily on hand-crafted features and domain-specific knowledge in order to learn effectively from the small, supervised training corpora that are available. In this paper, we introduce two new neural architectures—one based on bidirectional LSTMs and conditional random fields, and the other that constructs …...