arXiv subjects

I. Dan Melamed

Publications and source records attributed to I. Dan Melamed.

15 recordsLinked to original sources

arXiv2016

Towards A Virtual Assistant That Can Be Taught New Tasks In Any Domain By Its End-Users

The challenge stated in the title can be divided into two main problems. The first problem is to reliably mimic the way that users interact with user interfaces. The second problem is to build an instructible agent, i.e. one that can be taught to execute tasks expressed as previously unseen natural language commands. This paper proposes a solution to the second problem, a system we call Helpa. End-users can teach Helpa arbitrary new tasks whose level of complexity is similar to the tasks available from today's most popular virtual assistants. Teaching Helpa does not involve any programming. Instead, users teach Helpa by providing just one example of a command paired with a demonstration of how to execute that command. Helpa does not rely on any pre-existing domain-specific knowledge. It is therefore completely domain-independent. Our usability study showed that end-users can teach Helpa many new tasks in less than a minute each, often much less.

cs.AI↗

arXiv2005

Statistical Machine Translation by Generalized Parsing

Designers of statistical machine translation (SMT) systems have begun to employ tree-structured translation models. Systems involving tree-structured translation models tend to be complex. This article aims to reduce the conceptual complexity of such systems, in order to make them easier to design, implement, debug, use, study, understand, explain, modify, and improve. In service of this goal, the article extends the theory of semiring parsing to arrive at a novel abstract parsing algorithm with five functional parameters: a logic, a grammar, a semiring, a search strategy, and a termination condition. The article then shows that all the common algorithms that revolve around tree-structured translation models, including hierarchical alignment, inference for parameter estimation, translation, and structured evaluation, can be derived by generalizing two of these parameters -- the grammar and the logic. The article culminates with a recipe for using such generalized parsers to train, apply, and evaluate an SMT system that is driven by tree-structured translation models.

cs.CL↗

arXiv2000

Tagger Evaluation Given Hierarchical Tag Sets

We present methods for evaluating human and automatic taggers that extend current practice in three ways. First, we show how to evaluate taggers that assign multiple tags to each test instance, even if they do not assign probabilities. Second, we show how to accommodate a common property of manually constructed ``gold standards'' that are typically used for objective evaluation, namely that there is often more than one correct answer. Third, we show how to measure performance when the set of possible tags is tree-structured in an IS-A hierarchy. To illustrate how our methods can be used to measure inter-annotator agreement, we show how to compute the kappa coefficient over hierarchical tag sets.

cs.CL↗

arXiv1998

Manual Annotation of Translational Equivalence: The Blinker Project

Bilingual annotators were paid to link roughly sixteen thousand corresponding words between on-line versions of the Bible in modern French and modern English. These annotations are freely available to the research community from http://www.cis.upenn.edu/~melamed . The annotations can be used for several purposes. First, they can be used as a standard data set for developing and testing translation lexicons and statistical translation models. Second, researchers in lexical semantics will be able to mine the annotations for insights about cross-linguistic lexicalization patterns. Third, the annotations can be used in research into certain recently proposed methods for monolingual word-sense disambiguation. This paper describes the annotated texts, the specially-designed annotation tool, and the strategies employed to increase the consistency of the annotations. The annotation process was repeated five times by different annotators. Inter-annotator agreement rates indicate that the annotations are reasonably reliable and that the method is easy to replicate.

cmp-lg↗

arXiv1998

Word-to-Word Models of Translational Equivalence

Parallel texts (bitexts) have properties that distinguish them from other kinds of parallel data. First, most words translate to only one other word. Second, bitext correspondence is noisy. This article presents methods for biasing statistical translation models to reflect these properties. Analysis of the expected behavior of these biases in the presence of sparse data predicts that they will result in more accurate models. The prediction is confirmed by evaluation with respect to a gold standard -- translation models that are biased in this fashion are significantly more accurate than a baseline knowledge-poor model. This article also shows how a statistical translation model can take advantage of various kinds of pre-existing knowledge that might be available about particular language pairs. Even the simplest kinds of language-specific knowledge, such as the distinction between content words and function words, is shown to reliably boost translation model performance on some tasks. Statistical models that are informed by pre-existing knowledge about the model domain combine the best of both the rationalist and empiricist traditions.

cmp-lg↗

arXiv1998

Models of Co-occurrence

A model of co-occurrence in bitext is a boolean predicate that indicates whether a given pair of word tokens co-occur in corresponding regions of the bitext space. Co-occurrence is a precondition for the possibility that two tokens might be mutual translations. Models of co-occurrence are the glue that binds methods for mapping bitext correspondence with methods for estimating translation models into an integrated system for exploiting parallel texts. Different models of co-occurrence are possible, depending on the kind of bitext map that is available, the language-specific information that is available, and the assumptions made about the nature of translational equivalence. Although most statistical translation models are based on models of co-occurrence, modeling co-occurrence correctly is more difficult than it may at first appear.

cmp-lg↗

arXiv1998

Annotation Style Guide for the Blinker Project

This annotation style guide was created by and for the Blinker project at the University of Pennsylvania. The Blinker project was so named after the ``bilingual linker'' GUI, which was created to enable bilingual annotators to ``link'' word tokens that are mutual translations in parallel texts. The parallel text chosen for this project was the Bible, because it is probably the easiest text to obtain in electronic form in multiple languages. The languages involved were English and French, because, of the languages with which the project co-ordinator was familiar, these were the two for which a sufficient number of annotators was likely to be found.

cmp-lg↗

arXiv1997

A Portable Algorithm for Mapping Bitext Correspondence

The first step in most empirical work in multilingual NLP is to construct maps of the correspondence between texts and their translations ({\bf bitext maps}). The Smooth Injective Map Recognizer (SIMR) algorithm presented here is a generic pattern recognition algorithm that is particularly well-suited to mapping bitext correspondence. SIMR is faster and significantly more accurate than other algorithms in the literature. The algorithm is robust enough to use on noisy texts, such as those resulting from OCR input, and on translations that are not very literal. SIMR encapsulates its language-specific heuristics, so that it can be ported to any language pair with a minimal effort.

cmp-lg↗

arXiv1997

A Word-to-Word Model of Translational Equivalence

Many multilingual NLP applications need to translate words between different languages, but cannot afford the computational expense of inducing or applying a full translation model. For these applications, we have designed a fast algorithm for estimating a partial translation model, which accounts for translational equivalence only at the word level. The model's precision/recall trade-off can be directly controlled via one threshold parameter. This feature makes the model more suitable for applications that are not fully statistical. The model's hidden parameters can be easily conditioned on information extrinsic to the model, providing an easy way to integrate pre-existing knowledge such as part-of-speech, dictionaries, word order, etc.. Our model can link word tokens in parallel texts as well as other translation models in the literature. Unlike other translation models, it can automatically produce dictionary-sized translation lexicons, and it can do so with over 99% accuracy.

cmp-lg↗

arXiv1997

Automatic Discovery of Non-Compositional Compounds in Parallel Data

Automatic segmentation of text into minimal content-bearing units is an unsolved problem even for languages like English. Spaces between words offer an easy first approximation, but this approximation is not good enough for machine translation (MT), where many word sequences are not translated word-for-word. This paper presents an efficient automatic method for discovering sequences of words that are translated as a unit. The method proceeds by comparing pairs of statistical translation models induced from parallel texts in two languages. It can discover hundreds of non-compositional compounds on each iteration, and constructs longer compounds out of shorter ones. Objective evaluation on a simple machine translation task has shown the method's potential to improve the quality of MT output. The method makes few assumptions about the data, so it can be applied to parallel data other than parallel texts, such as word spellings and pronunciations.

cmp-lg↗

arXiv1997

Semi-Automatic Acquisition of Domain-Specific Translation Lexicons

We investigate the utility of an algorithm for translation lexicon acquisition (SABLE), used previously on a very large corpus to acquire general translation lexicons, when that algorithm is applied to a much smaller corpus to produce candidates for domain-specific translation lexicons.

cmp-lg↗

arXiv1996

A Geometric Approach to Mapping Bitext Correspondence

The first step in most corpus-based multilingual NLP work is to construct a detailed map of the correspondence between a text and its translation. Several automatic methods for this task have been proposed in recent years. Yet even the best of these methods can err by several typeset pages. The Smooth Injective Map Recognizer (SIMR) is a new bitext mapping algorithm. SIMR's errors are smaller than those of the previous front-runner by more than a factor of 4. Its robustness has enabled new commercial-quality applications. The greedy nature of the algorithm makes it independent of memory resources. Unlike other bitext mapping algorithms, SIMR allows crossing correspondences to account for word order differences. Its output can be converted quickly and easily into a sentence alignment. SIMR's output has been used to align over 200 megabytes of the Canadian Hansards for publication by the Linguistic Data Consortium.

cmp-lg↗

arXiv1996

Automatic Detection of Omissions in Translations

ADOMIT is an algorithm for Automatic Detection of OMIssions in Translations. The algorithm relies solely on geometric analysis of bitext maps and uses no linguistic information. This property allows it to deal equally well with omissions that do not correspond to linguistic units, such as might result from word-processing mishaps. ADOMIT has proven itself by discovering many errors in a hand-constructed gold standard for evaluating bitext mapping algorithms. Quantitative evaluation on simulated omissions showed that, even with today's poor bitext mapping technology, ADOMIT is a valuable quality control tool for translators and translation bureaus.

cmp-lg↗

arXiv1996

Automatic Construction of Clean Broad-Coverage Translation Lexicons

Word-level translational equivalences can be extracted from parallel texts by surprisingly simple statistical techniques. However, these techniques are easily fooled by {\em indirect associations} --- pairs of unrelated words whose statistical properties resemble those of mutual translations. Indirect associations pollute the resulting translation lexicons, drastically reducing their precision. This paper presents an iterative lexicon cleaning method. On each iteration, most of the remaining incorrect lexicon entries are filtered out, without significant degradation in recall. This lexicon cleaning technique can produce translation lexicons with recall and precision both exceeding 90\%, as well as dictionary-sized translation lexicons that are over 99\% correct.

cmp-lg↗

arXiv1995

Automatic Evaluation and Uniform Filter Cascades for Inducing N-Best Translation Lexicons

This paper shows how to induce an N-best translation lexicon from a bilingual text corpus using statistical properties of the corpus together with four external knowledge sources. The knowledge sources are cast as filters, so that any subset of them can be cascaded in a uniform framework. A new objective evaluation measure is used to compare the quality of lexicons induced with different filter cascades. The best filter cascades improve lexicon quality by up to 137% over the plain vanilla statistical method, and approach human performance. Drastically reducing the size of the training corpus has a much smaller impact on lexicon quality when these knowledge sources are used. This makes it practical to train on small hand-built corpora for language pairs where large bilingual corpora are unavailable. Moreover, three of the four filters prove useful even when used with large training corpora.

cmp-lg↗