Comunicacio presentada a la 2016 Conference of the North American Chapter of the Association for Computational Linguistics, celebrada a San Diego (CA, EUA) els dies 12 a 17 de juny 2016.

/pdf/neural-architectures-for-named-entity-recognition-4xswt97nv2.pdf

Neural Architectures for Named Entity Recognition

We present a lexicon-based approach to extracting sentiment from text. The Semantic Orientation CALculator (SO-CAL) uses dictionaries of words annotated with their semantic orientation (polarity and strength), and incorporates intensification and negation. SO-CAL is applied to the polarity classification task, the process of assigning a positive or negative label to a text that captures the text's opinion towards its main subject matter. We show that SO-CAL's performance is consistent across domains and in completely unseen data. Additionally, we describe the process of dictionary creation, and our use of Mechanical Turk to check dictionaries for consistency and reliability.

Lexicon-based methods for sentiment analysis

Summarization based on text extraction is inherently limited, but generation-style abstractive methods have proven challenging to build. In this work, we propose a fully data-driven approach to abstractive sentence summarization. Our method utilizes a local attention-based model that generates each word of the summary conditioned on the input sentence. While the model is structurally simple, it can easily be trained end-to-end and scales to a large amount of training data. The model shows significant performance gains on the DUC-2004 shared task compared with several strong baselines.

/pdf/a-neural-attention-model-for-abstractive-sentence-2hnbcyo1jn.pdf

A Neural Attention Model for Abstractive Sentence Summarization

This paper describes Meteor Universal, released for the 2014 ACL Workshop on Statistical Machine Translation. Meteor Universal brings language specific evaluation to previously unsupported target languages by (1) automatically extracting linguistic resources (paraphrase tables and function word lists) from the bitext used to train MT systems and (2) using a universal parameter set learned from pooling human judgments of translation quality from several language directions. Meteor Universal is shown to significantly outperform baseline BLEU on two new languages, Russian (WMT13) and Hindi (WMT14).

/pdf/meteor-universal-language-specific-translation-evaluation-1d9o0peq5a.pdf

Meteor Universal: Language Specific Translation Evaluation for Any Target Language

We present KenLM, a library that implements two data structures for efficient language model queries, reducing both time and memory costs. The Probing data structure uses linear probing hash tables and is designed for speed. Compared with the widely-used SRILM, our Probing model is 2.4 times as fast while using 57% of the memory. The Trie data structure is a trie with bit-level packing, sorted records, interpolation search, and optional quantization aimed at lower memory consumption. Trie simultaneously uses less memory than the smallest lossless baseline and less CPU than the fastest baseline. Our code is open-source, thread-safe, and integrated into the Moses, cdec, and Joshua translation systems. This paper describes the several performance techniques used and presents benchmarks against alternative implementations.

/pdf/kenlm-faster-and-smaller-language-model-queries-2ddzwlh35r.pdf

KenLM: Faster and Smaller Language Model Queries

Naively collecting translations by crowd-sourcing the task to non-professional translators yields disfluent, low-quality results if no quality control is exercised. We demonstrate a variety of mechanisms that increase the translation quality to near professional levels. Specifically, we solicit redundant translations and edits to them, and automatically select the best output among them. We propose a set of features that model both the translations and the translators, such as country of residence, LM perplexity of the translation, edit rate from the other translations, and (optionally) calibration against professional translators. Using these features to score the collected translations, we are able to discriminate between acceptable and unacceptable translations. We recreate the NIST 2009 Urdu-to-English evaluation set with Mechanical Turk, and quantitatively show that our models are able to select translations within the range of quality that we expect from professional translators. The total cost is more than an order of magnitude lower than professional translation.

/pdf/crowdsourcing-translation-professional-quality-from-non-4pihehjmlq.pdf

Crowdsourcing Translation: Professional Quality from Non-Professionals

We propose a new framework for supervised machine learning. Our goal is to learn from smaller amounts of supervised training data, by collecting a richer kind of training data: annotations with “rationales.” When annotating an example, the human teacher will also highlight evidence supporting this annotation—thereby teaching the machine learner why the example belongs to the category. We provide some rationale-annotated data and present a learning method that exploits the rationales during training to boost performance significantly on a sample task, namely sentiment classification of movie reviews. We hypothesize that in some situations, providing rationales is a more fruitful use of an annotator’s time than annotating more examples.

/pdf/using-annotator-rationales-to-improve-machine-learning-for-5feweswu5w.pdf

Using ``Annotator Rationales'' to Improve Machine Learning for Text Categorization

The written form of the Arabic language, Modern Standard Arabic MSA, differs in a non-trivial manner from the various spoken regional dialects of Arabic "the true native language"i¾of Arabic speakers. Those dialects, in turn, differ quite a bit from each other. However, due to MSA's prevalence in written form, almost all Arabic data sets have predominantly MSA content. In this article, we describe the creation of a novel Arabic resource with dialect annotations. We have created a large monolingual data set rich in dialectal Arabic content called the Arabic On-line Commentary Data set Zaidan and Callison-Burch 2011. We describe our annotation effort to identify the dialect level and dialect itself in each of more than 100,000 sentences from the data set by crowdsourcing the annotation task, and delve into interesting annotator behaviors like over-identification of one's own dialect. Using this new annotated data set, we consider the task of Arabic dialect identification: Given the word sequence forming an Arabic sentence, determine the variety of Arabic in which it is written. We use the data to train and evaluate automatic classifiers for dialect identification, and establish that classifiers using dialectal data significantly and dramatically outperform baselines that use MSA-only data, achieving near-human classification accuracy. Finally, we apply our classifiers to discover dialectical data from a large Web crawl consisting of 3.5 million pages mined from on-line Arabic newspapers.

/pdf/arabic-dialect-identification-4is6g5xvag.pdf

Arabic dialect identification

This paper presents the results of the WMT11 shared tasks, which included a translation task, a system combination task, and a task for machine translation evaluation metrics. We conducted a large-scale manual evaluation of 148 machine translation systems and 41 system combination entries. We used the ranking of these systems to measure how strongly automatic metrics correlate with human judgments of translation quality for 21 evaluation metrics. This year featured a Haitian Creole to English task translating SMS messages sent to an emergency response service in the aftermath of the Haitian earthquake. We also conducted a pilot 'tunable metrics' task to test whether optimizing a fixed system to different metrics would result in perceptibly different translation quality.

Findings of the 2011 Workshop on Statistical Machine Translation

This paper presents the results of the WMT10 and MetricsMATR10 shared tasks, which included a translation task, a system combination task, and an evaluation task. We conducted a large-scale manual evaluation of 104 machine translation systems and 41 system combination entries. We used the ranking of these systems to measure how strongly automatic metrics correlate with human judgments of translation quality for 26 metrics. This year we also investigated increasing the number of human judgments by hiring non-expert annotators through Amazon's Mechanical Turk.

/pdf/findings-of-the-2010-joint-workshop-on-statistical-machine-w6tdteyt5n.pdf

Omar F. Zaidan

Papers

Crowdsourcing Translation: Professional Quality from Non-Professionals

Using ``Annotator Rationales'' to Improve Machine Learning for Text Categorization

Arabic dialect identification

Findings of the 2011 Workshop on Statistical Machine Translation

Findings of the 2010 Joint Workshop on Statistical Machine Translation and Metrics for Machine Translation