arXiv subjects

Preslav Nakov

Publications and source records attributed to Preslav Nakov.

336 records · Page 19Linked to original sources

arXiv2017

Discourse Structure in Machine Translation Evaluation

In this article, we explore the potential of using sentence-level discourse structure for machine translation evaluation. We first design discourse-aware similarity measures, which use all-subtree kernels to compare discourse parse trees in accordance with the Rhetorical Structure Theory (RST). Then, we show that a simple linear combination with these measures can help improve various existing machine translation evaluation metrics regarding correlation with human judgments both at the segment- and at the system-level. This suggests that discourse information is complementary to the information used by many of the existing evaluation metrics, and thus it could be taken into account when developing richer evaluation metrics, such as the WMT-14 winning combined metric DiscoTKparty. We also provide a detailed analysis of the relevance of various discourse elements and relations from the RST parse trees for machine translation evaluation. In particular we show that: (i) all aspects of the RST tree are relevant, (ii) nuclearity is more useful than relation type, and (iii) the similarity of the translation RST tree to the reference tree is positively correlated with translation quality.

cs.CL↗

arXiv2017

Building Chatbots from Forum Data: Model Selection Using Question Answering Metrics

We propose to use question answering (QA) data from Web forums to train chatbots from scratch, i.e., without dialog training data. First, we extract pairs of question and answer sentences from the typically much longer texts of questions and answers in a forum. We then use these shorter texts to train seq2seq models in a more efficient way. We further improve the parameter optimization using a new model selection strategy based on QA measures. Finally, we propose to use extrinsic evaluation with respect to a QA task as an automatic evaluation method for chatbots. The evaluation shows that the model achieves a MAP of 63.5% on the extrinsic task. Moreover, it can answer correctly 49.5% of the questions when they are similar to questions asked in the forum, and 47.3% of the questions when they are more conversational in style.

cs.CL↗

arXiv2017

Fully Automated Fact Checking Using External Sources

Given the constantly growing proliferation of false claims online in recent years, there has been also a growing research interest in automatically distinguishing false rumors from factually true claims. Here, we propose a general-purpose framework for fully-automatic fact checking using external sources, tapping the potential of the entire Web as a knowledge source to confirm or reject a claim. Our framework uses a deep neural network with LSTM text encoding to combine semantic kernels with task-specific embeddings that encode a claim together with pieces of potentially-relevant text fragments from the Web, taking the source reliability into account. The evaluation results show good performance on two different tasks and datasets: (i) rumor detection and (ii) fact checking of the answers to a question in community question answering forums.

cs.CL↗

arXiv2017

Robust Tuning Datasets for Statistical Machine Translation

We explore the idea of automatically crafting a tuning dataset for Statistical Machine Translation (SMT) that makes the hyper-parameters of the SMT system more robust with respect to some specific deficiencies of the parameter tuning algorithms. This is an under-explored research direction, which can allow better parameter tuning. In this paper, we achieve this goal by selecting a subset of the available sentence pairs, which are more suitable for specific combinations of optimizers, objective functions, and evaluation measures. We demonstrate the potential of the idea with the pairwise ranking optimization (PRO) optimizer, which is known to yield too short translations. We show that the learning problem can be alleviated by tuning on a subset of the development set, selected based on sentence length. In particular, using the longest 50% of the tuning sentences, we achieve two-fold tuning speedup, and improvements in BLEU score that rival those of alternatives, which fix BLEU+1's smoothing instead.

cs.CL↗

arXiv2017

WERd: Using Social Text Spelling Variants for Evaluating Dialectal Speech Recognition

We study the problem of evaluating automatic speech recognition (ASR) systems that target dialectal speech input. A major challenge in this case is that the orthography of dialects is typically not standardized. From an ASR evaluation perspective, this means that there is no clear gold standard for the expected output, and several possible outputs could be considered correct according to different human annotators, which makes standard word error rate (WER) inadequate as an evaluation metric. Such a situation is typical for machine translation (MT), and thus we borrow ideas from an MT evaluation metric, namely TERp, an extension of translation error rate which is closely-related to WER. In particular, in the process of comparing a hypothesis to a reference, we make use of spelling variants for words and phrases, which we mine from Twitter in an unsupervised fashion. Our experiments with evaluating ASR output for Egyptian Arabic, and further manual analysis, show that the resulting WERd (i.e., WER for dialects) metric, a variant of TERp, is more adequate than WER for evaluating dialectal ASR.

cs.CL↗

arXiv2017

The Case for Being Average: A Mediocrity Approach to Style Masking and Author Obfuscation

Users posting online expect to remain anonymous unless they have logged in, which is often needed for them to be able to discuss freely on various topics. Preserving the anonymity of a text's writer can be also important in some other contexts, e.g., in the case of witness protection or anonymity programs. However, each person has his/her own style of writing, which can be analyzed using stylometry, and as a result, the true identity of the author of a piece of text can be revealed even if s/he has tried to hide it. Thus, it could be helpful to design automatic tools that can help a person obfuscate his/her identity when writing text. In particular, here we propose an approach that changes the text, so that it is pushed towards average values for some general stylometric characteristics, thus making the use of these characteristics less discriminative. The approach consists of three main steps: first, we calculate the values for some popular stylometric metrics that can indicate authorship; then we apply various transformations to the text, so that these metrics are adjusted towards the average level, while preserving the semantics and the soundness of the text; and finally, we add random noise. This approach turned out to be very efficient, and yielded the best performance on the Author Obfuscation task at the PAN-2016 competition.

cs.CL↗

arXiv2017

Seminar Users in the Arabic Twitter Sphere

We introduce the notion of "seminar users", who are social media users engaged in propaganda in support of a political entity. We develop a framework that can identify such users with 84.4% precision and 76.1% recall. While our dataset is from the Arab region, omitting language-specific features has only a minor impact on classification performance, and thus, our approach could work for detecting seminar users in other parts of the world and in other languages. We further explored a controversial political topic to observe the prevalence and potential potency of such users. In our case study, we found that 25% of the users engaged in the topic are in fact seminar users and their tweets make nearly a third of the on-topic tweets. Moreover, they are often successful in affecting mainstream discourse with coordinated hashtag campaigns.

cs.SI↗

arXiv2017

Large-Scale Goodness Polarity Lexicons for Community Question Answering

We transfer a key idea from the field of sentiment analysis to a new domain: community question answering (cQA). The cQA task we are interested in is the following: given a question and a thread of comments, we want to re-rank the comments so that the ones that are good answers to the question would be ranked higher than the bad ones. We notice that good vs. bad comments use specific vocabulary and that one can often predict the goodness/badness of a comment even ignoring the question, based on the comment contents only. This leads us to the idea to build a good/bad polarity lexicon as an analogy to the positive/negative sentiment polarity lexicons, commonly used in sentiment analysis. In particular, we use pointwise mutual information in order to build large-scale goodness polarity lexicons in a semi-supervised manner starting with a small number of initial seeds. The evaluation results show an improvement of 0.7 MAP points absolute over a very strong baseline and state-of-the art performance on SemEval-2016 Task 3.

cs.CL↗

arXiv2017

Cross-language Learning with Adversarial Neural Networks: Application to Community Question Answering

We address the problem of cross-language adaptation for question-question similarity reranking in community question answering, with the objective to port a system trained on one input language to another input language given labeled training data for the first language and only unlabeled data for the second language. In particular, we propose to use adversarial training of neural networks to learn high-level features that are discriminative for the main learning task, and at the same time are invariant across the input languages. The evaluation results show sizable improvements for our cross-language adversarial neural network (CLANN) model over a strong non-adversarial system.

cs.CL↗

arXiv2016

Enabling Medical Translation for Low-Resource Languages

We present research towards bridging the language gap between migrant workers in Qatar and medical staff. In particular, we present the first steps towards the development of a real-world Hindi-English machine translation system for doctor-patient communication. As this is a low-resource language pair, especially for speech and for the medical domain, our initial focus has been on gathering suitable training data from various sources. We applied a variety of methods ranging from fully automatic extraction from the Web to manual annotation of test data. Moreover, we developed a method for automatically augmenting the training data with synthetically generated variants, which yielded a very sizable improvement of more than 3 BLEU points absolute.

cs.CL↗

arXiv2016

Bi-Text Alignment of Movie Subtitles for Spoken English-Arabic Statistical Machine Translation

We describe efforts towards getting better resources for English-Arabic machine translation of spoken text. In particular, we look at movie subtitles as a unique, rich resource, as subtitles in one language often get translated into other languages. Movie subtitles are not new as a resource and have been explored in previous research; however, here we create a much larger bi-text (the biggest to date), and we further generate better quality alignment for it. Given the subtitles for the same movie in different languages, a key problem is how to align them at the fragment level. Typically, this is done using length-based alignment, but for movie subtitles, there is also time information. Here we exploit this information to develop an original algorithm that outperforms the current best subtitle alignment tool, subalign. The evaluation results show that adding our bi-text to the IWSLT training bi-text yields an improvement of over two BLEU points absolute.

cs.CL↗

arXiv2016

Egyptian Arabic to English Statistical Machine Translation System for NIST OpenMT'2015

The paper describes the Egyptian Arabic-to-English statistical machine translation (SMT) system that the QCRI-Columbia-NYUAD (QCN) group submitted to the NIST OpenMT'2015 competition. The competition focused on informal dialectal Arabic, as used in SMS, chat, and speech. Thus, our efforts focused on processing and standardizing Arabic, e.g., using tools such as 3arrib and MADAMIRA. We further trained a phrase-based SMT system using state-of-the-art features and components such as operation sequence model, class-based language model, sparse features, neural network joint model, genre-based hierarchically-interpolated language model, unsupervised transliteration mining, phrase-table merging, and hypothesis combination. Our system ranked second on all three genres.

cs.CL↗