Computer Science Theses and Dissertations
Permanent URI for this collectionhttp://hdl.handle.net/1903/2756
Browse
6 results
Search Results
Item DETECTING FINE-GRAINED SEMANTIC DIVERGENCES TO IMPROVE TRANSLATION UNDERSTANDING ACROSS LANGUAGES(2023) Briakou, Eleftheria; Carpuat, Marine; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)One of the core goals of Natural Language Processing (NLP) is to develop computationalrepresentations and methods to compare and contrast text meaning across languages. Such methods are essential to many NLP tasks, such as question answering and information retrieval. One of the limitations of those methods is the lack of sensitivity to detecting fine-grained semantic divergences, i.e., fine-meaning differences in sentences that overlap in content. Yet, such differences abound even in parallel texts, i.e., texts in two different languages that are typically perceived as exact translations of each other. Detecting such fine-grained semantic divergences across languages matters for machine translation systems, as they yield challenging training samples and for humans, who can benefit from a nuanced understanding of the source. In this thesis, we focus on detecting fine-grained semantic divergences in parallel textsto improve machine and human translation understanding. In our first piece of work, we start by providing empirical evidence that such small meaning differences exist and can be reliably annotated both at a sentence and at a sub-sentential level. Then, we show that they can be automatically detected by fine-tuning large pre-trained language models without supervision by learning to rank synthetic divergences of varying granularity. In our second piece of work, we turn to analyzing the impact of fine-grained divergences on Neural Machine Translation (NMT) training and show that they negatively impact several aspects of NMT outputs, e.g., translation quality and confidence. Based on these findings, we present two orthogonal approaches to mitigating the negative impact of divergences and improve machine translation quality: first, we introduce a divergent-aware NMT framework that models divergences at training time; second, we present generation-based approaches for revising divergences in mined parallel texts to make the corresponding references more equivalent in meaning. After exploring how subtle meaning differences in parallel texts impact machine translationsystems, we switch gears to understand how divergence detection can be used by humans directly. In our last piece of work, we extend our divergence detection methods to explain divergences from a human-centered perspective. We introduce a lightweight iterative algorithm that extracts contrastive phrasal highlights, i.e., highlights of segments indicating where divergences reside within bilingual texts, by explicitly formalizing the alignment between them. We show that our approach produces contrastive phrasal highlights that match human-provided rationales of divergences better than prior explainability approaches. Finally, based on extensive application-grounded evaluations, we show that contrastive phrasal highlights help bilingual speakers detect fine-grained meaning differences in human-translated texts, as well as critical errors due to local mistranslations in machine-translated texts.Item Identifying Semantic Divergences Across Languages(2019) Vyas, Yogarshi; Carpuat, Marine; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Cross-lingual resources such as parallel corpora and bilingual dictionaries are cornerstones of multilingual natural language processing (NLP). They have been used to study the nature of translation, train automatic machine translation systems, as well as to transfer models across languages for an array of NLP tasks. However, the majority of work in cross-lingual and multilingual NLP assumes that translations recorded in these resources are semantically equivalent. This is often not the case---words and sentences that are considered to be translations of each other frequently divergein meaning, often in systematic ways. In this thesis, we focus on such mismatches in meaning in text that we expect to be aligned across languages. We term such mismatches as cross-lingual semantic divergences. The core claim of this thesis is that translation is not always meaning preserving which leads to cross-lingual semantic divergences that affect multilingual NLP tasks. Detecting such divergences requires ways of directly characterizing differences in meaning across languages through novel cross-lingual tasks, as well as models that account for translation ambiguity and do not rely on expensive, task-specific supervision. We support this claim through three main contributions. First, we show that a large fraction of data in multilingual resources (such as parallel corpora and bilingual dictionaries) is identified as semantically divergent by human annotators. Second, we introduce cross-lingual tasks that characterize differences in word meaning across languages by identifying the semantic relation between two words. We also develop methods to predict such semantic relations, as well as a model to predict whether sentences in different languages have the same meaning. Finally, we demonstrate the impact of divergences by applying the methods developed in the previous sections to two downstream tasks. We first show that our model for identifying semantic relations between words helps in separating equivalent word translations from divergent translations in the context of bilingual dictionary induction, even when the two words are close in meaning. We also show that identifying and filtering semantic divergences in parallel data helps in training a neural machine translation system twice as fast without sacrificing quality.Item Formality Style Transfer Within and Across Languages with Limited Supervision(2019) Niu, Xing; Carpuat, Marine; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)While much natural language processing work focuses on analyzing language content, language style also conveys important information about the situational context and purpose of communication. When editing an article, professional editors take into account the target audience to select appropriate word choice and grammar. Similarly, professional translators translate documents for a specific audience and often ask what is the expected tone of the content when taking a translation job. Computational models of natural language should consider both their meaning and style. Controlling style is an emerging research area in text rewriting and is under-investigated in machine translation. In this dissertation, we present a new perspective which closely connects formality transfer and machine translation: we aim to control style in language generation with a focus on rewriting English or translating French to English with a desired formality. These are challenging tasks because annotated examples of style transfer are only available in limited quantities. We first address this problem by inducing a lexical formality model based on word embeddings and a small number of representative formal and informal words. This enables us to assign sentential formality scores and rerank translation hypotheses whose formality scores are closer to user-provided formality level. To capture broader formality changes, we then turn to neural sequence to sequence models. Joint modeling of formality transfer and machine translation enables formality control in machine translation without dedicated training examples. Along the way, we also improve low-resource neural machine translation.Item Searching to Translate and Translating to Search: When Information Retrieval Meets Machine Translation(2013) Ture, Ferhan; Lin, Jimmy; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)With the adoption of web services in daily life, people have access to tremendous amounts of information, beyond any human's reading and comprehension capabilities. As a result, search technologies have become a fundamental tool for accessing information. Furthermore, the web contains information in multiple languages, introducing another barrier between people and information. Therefore, search technologies need to handle content written in multiple languages, which requires techniques to account for the linguistic differences. Information Retrieval (IR) is the study of search techniques, in which the task is to find material relevant to a given information need. Cross-Language Information Retrieval (CLIR) is a special case of IR when the search takes place in a multi-lingual collection. Of course, it is not helpful to retrieve content in languages the user cannot understand. Machine Translation (MT) studies the translation of text from one language into another efficiently (within a reasonable amount of time) and effectively (fluent and retaining the original meaning), which helps people understand what is being written, regardless of the source language. Putting these together, we observe that search and translation technologies are part of an important user application, calling for a better integration of search (IR) and translation (MT), since these two technologies need to work together to produce high-quality output. In this dissertation, the main goal is to build better connections between IR and MT, for which we present solutions to two problems: Searching to translate explores approximate search techniques for extracting bilingual data from multilingual Wikipedia collections to train better translation models. Translating to search explores the integration of a modern statistical MT system into the cross-language search processes. In both cases, our best-performing approach yielded improvements over strong baselines for a variety of language pairs. Finally, we propose a general architecture, in which various components of IR and MT systems can be connected together into a feedback loop, with potential improvements to both search and translation tasks. We hope that the ideas presented in this dissertation will spur more interest in the integration of search and translation technologies.Item Modeling Dependencies in Natural Languages with Latent Variables(2011) Huang, Zhongqiang; Harper, Mary; Resnik, Philip; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)In this thesis, we investigate the use of latent variables to model complex dependencies in natural languages. Traditional models, which have a fixed parameterization, often make strong independence assumptions that lead to poor performance. This problem is often addressed by incorporating additional dependencies into the model (e.g., using higher order N-grams for language modeling). These added dependencies can increase data sparsity and/or require expert knowledge, together with trial and error, in order to identify and incorporate the most important dependencies (as in lexicalized parsing models). Traditional models, when developed for a particular genre, domain, or language, are also often difficult to adapt to another. In contrast, previous work has shown that latent variable models, which automatically learn dependencies in a data-driven way, are able to flexibly adjust the number of parameters based on the type and the amount of training data available. We have created several different types of latent variable models for a diverse set of natural language processing applications, including novel models for part-of-speech tagging, language modeling, and machine translation, and an improved model for parsing. These models perform significantly better than traditional models. We have also created and evaluated three different methods for improving the performance of latent variable models. While these methods can be applied to any of our applications, we focus our experiments on parsing. The first method involves self-training, i.e., we train models using a combination of gold standard training data and a large amount of automatically labeled training data. We conclude from a series of experiments that the latent variable models benefit much more from self-training than conventional models, apparently due to their flexibility to adjust their model parameterization to learn more accurate models from the additional automatically labeled training data. The second method takes advantage of the variability among latent variable models to combine multiple models for enhanced performance. We investigate several different training protocols to combine self-training with model combination. We conclude that these two techniques are complementary to each other and can be effectively combined to train very high quality parsing models. The third method replaces the generative multinomial lexical model of latent variable grammars with a feature-rich log-linear lexical model to provide a principled solution to address data sparsity, handle out-of-vocabulary words, and exploit overlapping features during model induction. We conclude from experiments that the resulting grammars are able to effectively parse three different languages. This work contributes to natural language processing by creating flexible and effective latent variable models for several different languages. Our investigation of self-training, model combination, and log-linear models also provides insights into the effective application of these machine learning techniques to other disciplines.Item Lexical Features for Statistical Machine Translation(2009) Devlin, Jacob; Dorr, Bonnie; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)In modern phrasal and hierarchical statistical machine translation systems, two major features model translation: rule translation probabilities and lexical smoothing scores. The rule translation probabilities are computed as maximum likelihood estimates (MLEs) of an entire source (or target) phrase translating to a target (or source) phrase. The lexical smoothing scores are also a likelihood estimate of a source (target) phrase translating to a target (source) phrase, but they are computed using independent word-to-word translation probabilities. Intuitively, it would seem that the lexical smoothing score is a less powerful estimate of translation likelihood due to this independence assumption, but I present the somewhat surprising result that lexical smoothing is far more important to the quality of a state-of-the-art hierarchical SMT system than rule translation probabilities. I posit that this is due to a fundamental data sparsity problem: The average word-to-word translation is seen many more times than the average phrase-to-phrase translation, so the word-to-word translation probabilities (or lexical probabilities) are far better estimated. Motivated by this result, I present a number of novel methods for modifying the lexical probabilities to improve the quality of our MT output. First, I examine two methods of lexical probability biasing, where for each test document, a set of secondary lexical probabilities are extracted and interpolated with the primary lexical probability distribution. Biasing each document with the probabilities extracted from its own first-pass decoding output provides a small but consistent gain of about 0.4 BLEU. Second, I contextualize the lexical probabilities by factoring in additional information such as the previous or next word. The key to the success of this context-dependent lexical smoothing is a backoff model, where our "trust" of a context-dependent probability estimation is directly proportional to how many times it was seen in the training. In this way, I avoid the estimation problem seen in translation rules, where the amount of context is high but the probability estimation is inaccurate. When using the surrounding words as context, this feature provides a gain of about 0.6 BLEU on Arabic and Chinese. Finally, I describe several types of discriminatively trained lexical features, along with a new optimization procedure called Expected-BLEU optimization. This new optimization procedure is able to robustly estimate weights for thousands of decoding features, which can in effect discriminatively optimize a set of lexical probabilities to maximize BLEU. I also describe two other discriminative feature types, one of which is the part-of-speech analogue to lexical probabilities, and the other of which estimates training corpus weights based on lexical translations. The discriminative features produce a gain of 0.8 BLEU on Arabic and 0.4 BLEU on Chinese.