EMNLP 2015 Papers

We introduce Trans-gram, a simple and computationally-efficient method to simultaneously learn and align wordembeddings for a variety of languages, using only monolingual data and a smaller set of sentence-aligned data. We use our new method to compute aligned wordembeddings for twenty-one languages using English as a pivot language. We show that some linguistic features are aligned across languages for which we do not have aligned data, even though those properties do not exist in the pivot language. We also achieve state of the art results on standard cross-lingual text classification and word translation tasks.

Language use is known to be influenced by personality traits as well as by sociodemographic characteristics such as age or mother tongue. As a result, it is possible to automatically identify these traits of the author from her texts. It has recently been shown that knowledge of such dimensions can improve performance in NLP tasks such as topic and sentiment modeling. We posit that machine translation is another application that should be personalized. In order to motivate this, we explore whether translation preserves demographic and psychometric traits. We show that, largely, both translation of the source training data into the target language, and the target test data into the source language has a detrimental effect on the accuracy of predicting author traits. We argue that this supports the need for personal and personality-aware machine translation models.

In syntax-based machine translation, rule selection is the task of choosing the correct target side of a translation rule among rules with the same source side. We define a discriminative rule selection model for systems that have syntactic annotation on the target language side (stringto-tree). This is a new and clean way to integrate soft source syntactic constraints into string-to-tree systems as features of the rule selection model. We release our implementation as part of Moses.

This paper proposes a method for hierarchical phrase-based stream decoding. A stream decoder is able to take a continuous stream of tokens as input, and segments this stream into word sequences that are translated and output as a stream of target word sequences. Phrase-based stream decoding techniques have been shown to be effective as a means of simultaneous interpretation. In this paper we transfer the essence of this idea into the framework of hierarchical machine translation. The hierarchical decoding framework organizes the decoding process into a chart; this structure is naturally suited to the process of stream decoding, leading to an efficient stream decoding algorithm that searches a restricted subspace containing only relevant hypotheses. Furthermore, the decoder allows more explicit access to the word re-ordering process that is of critical importance in decoding while interpreting. The decoder was evaluated on TED talk data for English-Spanish and English-Chinese. Our results show that like the phrase-based stream decoder, the hierarchical is capable of approaching the performance of the underlying hierarchical phrase-based machine translation decoder, at useful levels of latency. In addition the hierarchical approach appeared to be robust to the difficulties presented by the more challenging English-Chinese task.

This work focuses on the task of finding latent vector representations of the words in a corpus. In particular, we address the issue of what to do when there are multiple languages in the corpus. Prior work has, among other techniques, used canonical correlation analysis to project pre-trained vectors in two languages into a common space. We propose a simple and scalable method that is inspired by the notion that the learned vector representations should be invariant to translation between languages. We show empirically that our method outperforms prior work on multilingual tasks, matches the performance of prior work on monolingual tasks, and scales linearly with the size of the input data (and thus the number of languages being embedded).

In this paper, we develop a supervised learning technique that improves noisy phrase translation scores obtained by phrase table triangulation. In particular, we extract word translation distributions from small amounts of source-target bilingual data (a dictionary or a parallel corpus) with which we learn to assign better scores to translation candidates obtained by triangulation. Our method is able to gain improvement in translation quality on two tasks: (1) On Malagasy-to-French translation via English, we use only 1k dictionary entries to gain +0.5 Bleu over triangulation. (2) On Spanish-to-French via English we use only 4k sentence pairs to gain +0.7 Bleu over triangulation interpolated with a phrase table extracted from the same 4k sentence pairs.

We present novel features designed with a deep neural network for Machine Translation (MT) Quality Estimation (QE). The features are learned with a Continuous Space Language Model to estimate the probabilities of the source and target segments. These new features, along with standard MT system-independent features, are benchmarked on a series of datasets with various quality labels, including postediting effort, human translation edit rate, post-editing time and METEOR. Results show significant improvements in prediction over the baseline, as well as over systems trained on state of the art feature sets for all datasets. More notably, the addition of the newly proposed features improves over the best QE systems in WMT12 and WMT14 by a significant margin.

Many state-of-the-art Machine Translation (MT) evaluation metrics are complex, involve extensive external resources (e.g. for paraphrasing) and require tuning to achieve best results. We present a simple alternative approach based on dense vector spaces and recurrent neural networks (RNNs), in particular Long Short Term Memory (LSTM) networks. ForWMT-14, our new metric scores best for two out of five language pairs, and overall best and second best on all language pairs, using Spearman and Pearson correlation, respectively. We also show how training data is computed automatically from WMT ranks data.

We present an incremental adaptation approach for statistical machine translation that maintains a flexible hierarchical domain structure within a single consistent model. Both weights and rules are updated incrementallyonastreamofpost-edits. Our multi-level domain hierarchy allows the system to adapt simultaneously towards local context at dierent levels of granularity, including genres and individual documents. Our experiments show consistent improvements in translation quality from all components of our approach.

In this paper, we propose a paraphrasing model to address the task of system combination for machine translation. We dynamically learn hierarchical paraphrases from target hypotheses and form a synchronous context-free grammar to guide a series of transformations of target hypotheses into fused translations. The model is able to exploit phrasal and structural system-weighted consensus and also to utilize existing information about word ordering present in the target hypotheses. In addition, to consider a diverse set of plausible fused translations, we develop a hybrid combination architecture, where we paraphrase every target hypothesis using different fusing techniques to obtain fused translations for each target, and then make the final selection among all fused translations. Our experimental results show that our approach can achieve a significant improvement over combination baselines.

Continuous-space translation models have recently emerged as extremely powerful ways to boost the performance of existing translation systems. A simple, yet effective way to integrate such models in inference is to use them in an N -best rescoring step. In this paper, we focus on this scenario and show that the performance gains in rescoring can be greatly increased when the neural network is trained jointly with all the other model parameters, using an appropriate objective function. Our approach is validated on two domains, where it outperforms strong baselines.

We introduce pre-post-editing, possibly the most basic form of interactive translation, as a touch-based interaction with iteratively improved translation hypotheses prior to classical post-editing. We report simulated experiments that yield very large improvements on classical evaluation metrics (up to 21 BLEU) as well as on a parameterized variant of the TER metric that takes into account the cost of matching/touching tokens, confirming the promising prospects of the novel translation scenarios offered by our approach.

fast align is a simple, fast, and efficient approach for word alignment based on the IBM model 2. fast align performs well for language pairs with relatively similar word orders; however, it does not perform well for language pairs with drastically different word orders. We propose a segmenting-reversing reordering process to solve this problem by alternately applying fast align and reordering source sentences during training. Experimental results with JapaneseEnglish translation demonstrate that the proposed approach improves the performance of fast align significantly without the loss of efficiency. Experiments using other languages are also reported.

Logic grid puzzle is a genre of logic puzzles in which we are given (in a natural language) a scenario, the object to be deduced and certain clues. The reader has to figure out the solution using the clues provided and some generic domain constraints. In this paper, we present a system, LOGICIA, that takes a logic grid puzzle and the set of elements in the puzzle and tries to solve it by translating it to the knowledge representation and reasoning language of Answer Set Programming (ASP) and then using an ASP solver. The translation to ASP involves extraction of entities and their relations from the clues. For that we use a novel learning based approach which uses varied supervision, including the entities present in a clue and the expected representation of a clue in ASP. Our system, LOGICIA, learns to automatically translate a clue with 81.11% accuracy and is able to solve 71% of the problems of a corpus. This is the first learning system that can solve logic grid puzzles described in natural language in a fully automated manner. The code and the data will be made publicly available at http://bioai.lab . asu.edu/logicgridpuzzles.

Taxonomy plays an important role in many applications by organizing domain knowledge into a hierarchy of is-a relations between terms. Previous works on the taxonomic relation identification from text corpora lack in two aspects: 1) They do not consider the trustiness of individual source texts, which is important to filter out incorrect relations from unreliable sources. 2) They also do not consider collective evidence from synonyms and contrastive terms, where synonyms may provide additional supports to taxonomic relations, while contrastive terms may contradict them. In this paper, we present a method of taxonomic relation identification that incorporates the trustiness of source texts measured with such techniques as PageRank and knowledge-based trust, and the collective evidence of synonyms and contrastive terms identified by linguistic pattern matching and machine learning. The experimental results show that the proposed features can consistently improve performance up to 4%-10% of F-measure.

Sarcasm is generally characterized as a figure of speech that involves the substitution of a literal by a figurative meaning, which is usually the opposite of the original literal meaning. We re-frame the sarcasm detection task as a type of word sense disambiguation problem, where the sense of a word is either literal or sarcastic. We call this the Literal/Sarcastic Sense Disambiguation (LSSD) task. We address two issues: 1) how to collect a set of target words that can have either literal or sarcastic meanings depending on context; and 2) given an utterance and a target word, how to automatically detect whether the target word is used in the literal or the sarcastic sense. For the latter, we investigate several distributional semantics methods and show that a Support Vector Machines (SVM) classifier with a modified kernel using word embeddings achieves a 7-10% F1 improvement over a strong lexical baseline.

Comparison is one of the most important phenomena in language for expressing objective and subjective facts about various entities. Systems that can understand and reason over comparative structure can play a major role in the applications which require deeper understanding of language. In this paper we present a novel semantic framework for representing the meaning of comparative structures in natural language, which models comparisons as predicate-argument pairs interconnected with semantic roles. Our framework supports not only adjectival, but also adverbial, nominal, and verbal comparatives. With this paper, we provide a novel dataset of gold-standard comparison structures annotated according to our semantic framework.

We present an unsupervised hard EM approach to automatically mapping instructional recipes to action graphs, which define what actions should be performed on which objects and in what order. Recovering such structures can be challenging, due to unique properties of procedural language where, for example, verbal arguments are commonly elided when they can be inferred from context and disambiguation often requires world knowledge. Our probabilistic model incorporates aspects of procedural semantics and world knowledge, such as likely locations and selectional preferences for different actions. Experiments with cooking recipes demonstrate the ability to recover high quality action graphs, outperforming a strong sequential baseline by 8 points in F1, while also discovering general-purpose knowledge about cooking.

Relational phrases (e.g., “got married to”) and their hypernyms (e.g., “is a relative of”) are central for many tasks including question answering, open information extraction, paraphrasing, and entailment detection. This has motivated the development of several linguistic resources (e.g. DIRT, PATTY, and WiseNet) which systematically collect and organize relational phrases. These resources have demonstrable practical benefits, but are each limited due to noise, sparsity, or size. We present a new general-purpose method, RELLY, for constructing a large hypernymy graph of relational phrases with high-quality subsumptions using collective probabilistic programming techniques. Our graph induction approach integrates small highprecision knowledge bases together with large automatically curated resources, and reasons collectively to combine these resources into a consistent graph. Using RELLY, we construct a high-coverage, high-precision hypernymy graph consisting of 20K relational phrases and 35K hypernymy links. Our evaluation indicates a hypernymy link precision of 78%, and demonstrates the value of this resource for a document-relevance ranking task.