We introduce GenerativeDictionary, a novel dictionary system that generates word sense interpretations based on the given context. Our approach involves transforming context sentences to highlight the meaning of target words within their specific context. The method involves automatically transforming context sentences into sequences of low-dimensional vector token representations, automatically processing the input embeddings through multiple layers of transformers, and automatically generate the word senses based on the latent representations derived from the context. At runtime, context sentences with target words are processed through a transformer model that outputs the relevant word senses.Blind evaluations on a combined set of dictionary example sentences and generated sentences based on given word senses demonstrate that our method is comparable to traditional word sense disambiguation (WSD) methods. By framing WSD as a generative problem, GenerativeDictionary delivers more precise and contextually appropriate word senses, enhancing the effectiveness of language learning tools.

While sentence simplification is an active research topic in NLP, its adjacent tasks of sentence complexification and same-level paraphrasing are not. To train models on all three tasks, we present two new unsupervised datasets. We compare these datasets, one labeled by a weak classifier and the other by a rule-based approach, with a single supervised dataset. Using these three datasets for training, we perform extensive experiments on both multitasking and prompting strategies. Compared to other systems trained on unsupervised parallel data, models trained on our weak classifier labeled dataset achieve state-of-the-art performance on the ASSET simplification benchmark. Our models also outperform previous work on sentence-level targeting. Finally, we establish how a handful of Large Language Models perform on these tasks under a zero-shot setting.

Sentence alignment is an essential step in studying the mapping among different language expressions, and the character trigram overlapping ratio was reported to be the most effective similarity measure in aligning sentences in the text simplification dataset. However, the appropriateness of each similarity measure depends on the characteristics of the corpus to be aligned. This paper studies if the character trigram is still a suitable similarity measure for the task of aligning sentences in a paragraph paraphrasing corpus. We compare several embedding-based and non-embeddings model-agnostic similarity measures, including those that have not been studied previously. The evaluation is conducted on parallel paragraphs sampled from the Webis-CPC-11 corpus, which is a paragraph paraphrasing dataset. Our results show that modern BERT-based measures such as Sentence-BERT or BERTScore can lead to significant improvement in this task.

We introduce a method for generating error-correction rules for grammar pattern errors in a given annotated learner corpus. In our approach, annotated edits in the learner corpus are converted into edit rules for correcting common writing errors. The method involves automatic extraction of grammar patterns, and automatic alignment of the erroneous patterns and correct patterns. At run-time, grammar patterns are extracted from the grammatically correct sentences, and correction rules are retrieved by aligning the extracted grammar patterns with the erroneous patterns. Using the proposed method, we generate 1,499 high-quality correction rules related to 232 headwords. The method can be used to assist ESL students in avoiding grammatical errors, and aid teachers in correcting students’ essays. Additionally, the method can be used in the compilation of collocation error dictionaries and the construction of grammar error correction systems.

We introduce a method for assisting English as Second Language (ESL) learners by providing translations of Collins COBUILD grammar patterns(GP) for a given word. In our approach, bilingual parallel corpus is transformed into bilingual GP pairs aimed at providing native language support for learning word usage through GPs. The method involves automatically parsing sentences to extract GPs, automatically generating translation GP pairs from bilingual sentences, and automatically extracting common bilingual GPs. At run-time, the target word is used for lookup GPs and translations, and the retrieved common GPs and their example sentences are shown to the user. We present a prototype phrase search engine, Linggle GPTrans, that implements the methods to assist ESL learners. Preliminary evaluation on a set of more than 300 GP-translation pairs shows that the methods achieve 91% accuracy.

This paper presents a method for automatically identifying bilingual grammar patterns and extracting bilingual phrase instances from a given English-Chinese sentence pair. In our approach, the English-Chinese sentence pair is parsed to identify English grammar patterns and Chinese counterparts. The method involves generating translations of each English grammar pattern and calculating translation probability of words from a word-aligned parallel corpora. The results allow us to extract the most probable English-Chinese phrase pairs in the sentence pair. We present a prototype system that applies the method to extract grammar patterns and phrases in parallel sentences. An evaluation on randomly selected examples from a dictionary shows that our approach has reasonably good performance. We use human judge to assess the bilingual phrases generated by our approach. The results have potential to assist language learning and machine translation research.

We present a method for determining intended sense definitions of a given academic word in an academic keyword list. In our approach, the keyword list are converted into unigram of all possible Mandarin translations, intended or not. The method involve converting words in the keyword list into all translations using a bilingual dictionary, computing the unigram word counts of translations, and computing character counts from the word counts. At run-time, each definition (with associated translation) of the given word is scored with word and character counts, and the definition with the highest count is returned. We present a prototype system for the Academic Keyword List to generate definitions and translation for pedagogy purposes. We also experimented with clustering definition embeddings of all words and definitions, and identifying intended sense in favor of embedding in larger clusters. Preliminary evaluation shows promising performance. This endeavor is a step towards creating a full-fledged dictionary from an academic word list.

This paper presents LinggleWrite, a writing coach that provides writing suggestions, assesses writing proficiency levels, detects grammatical errors, and offers corrective feedback in response to user’s essay. The method involves extracting grammar patterns, training models for automated essay scoring (AES) and grammatical error detection (GED), and finally retrieving plausible corrections from a n-gram search engine. Experiments on public test sets indicate that both AES and GED models achieve state-of-the-art performance. These results show that LinggleWrite is potentially useful in helping learners improve their writing skills.

We present a writing prototype feedback system, TellMeWhy, to provide explanations of errors in submitted essays. In our approach, the sentence with corrections is analyzed to identify error types and problem words, aimed at customizing explanations based on the context of the error. The method involves learning the relation of errors and problem words, generating common feedback patterns, and extracting grammar patterns, collocations and example sentences. At run-time, a sentence with corrections is classified, and the problem word and template are identified to provide detailed explanations. Preliminary evaluation shows that the method has potential to improve existing commercial writing services.

We present a method for learning bilingual word embeddings in order to support second language (L2) learners in finding recurring phrases and example sentences that match mixed-code queries (e.g., “接 受 sentence”) composed of words in both target language and native language (L1). In our approach, mixed-code queries are transformed into target language queries aimed at maximizing the probability of retrieving relevant target language phrases and sentences. The method involves converting a given parallel corpus into mixed-code data, generating word embeddings from mixed-code data, and expanding queries in target languages based on bilingual word embeddings. We present a prototype search engine, x.Linggle, that applies the method to a linguistic search engine for a parallel corpus. Preliminary evaluation on a list of common word-translation shows that the method performs reasonablly well.

We introduce a method for generating suggestions on a given sentence for improving the proficiency level. In our approach, the sentence is transformed into a sequence of grammatical elements aimed at providing suggestions of more advanced grammar elements based on originals. The method involves parsing the sentence, identifying grammatical elements, and ranking related elements to recommend a higher level of grammatical element. We present a prototype tutoring system, Level-Up, that applies the method to English learners’ essays in order to assist them in writing and reading. Evaluation on a set of essays shows that our method does assist user in writing.

We introduce a system aimed at improving and expanding second language learners’ English vocabulary. In addition to word definitions, we provide rich lexical information such as collocations and grammar patterns for target words. We present Linggle Booster that takes an article, identifies target vocabulary, provides lexical information, and generates a quiz on target words. Linggle Booster also links named-entity to corresponding Wikipedia pages. Evaluation on a set of target words shows that the method have reasonably good performance in terms of generating useful and information for learning vocabulary.

This paper presents a grammatical error correction (GEC) system that provides corrective feedback for essays. We apply the sequence-to-sequence model, which is frequently used in machine translation and text summarization, to this GEC task. The model is trained by EF-Cambridge Open Language Database (EFCAMDAT), a large learner corpus annotated with grammatical errors and corrections. Evaluation shows that our system achieves competitive performance on a number of publicly available testsets.

In this paper, we present a system, LanguageNet, which can help second language learners to search for different meanings and usages of a word. We disambiguate word senses based on the pairs of an English word and its corresponding Chinese translations in a parallel corpus, UM-Corpus. The process involved performing word alignment, learning vector space representations of words and training a classifier to distinguish words into groups of senses. LanguageNet directly shows the definition of a sense, bilingual synonyms and sense relevant examples.

According to the analysis of Cambridge Learner Corpus, using a wrong verb is the most common type of grammatical errors. This paper describes Verb Replacer, a system for detecting and correcting potential verb errors in a given sentence. In our approach, alternative verbs are considered to replace the verb based on an error-annotated corpus and verb-object collocations. The method involves applying regression on channel models, parsing the sentence, identifying the verbs, retrieving a small set of alternative verbs, and evaluating each alternative. Our method combines and improves channel and language models, resulting in high recall of detecting and correcting verb misuse.

In this paper, we present a method for extracting Synchronous Grammar Patterns (SGPs) from a given parallel corpus in order to assisted second language learners in writing. A grammar pattern consists of a head word (verb, noun, or adjective) and its syntactic environment. A synchronous grammar pattern describes a grammar pattern in the target language (e.g., English) and its counterpart in an other language (e.g., Mandarin), serving the purpose of native language support. Our method involves identifying the grammar patterns in the target language, aligning these patterns with the target language patterns, and finally filtering valid SGPs. The extracted SGPs with examples are then used to develop a prototype writing assistant system, called WriteAhead/bilingual. Evaluation on a set of randomly selected SGPs shows that our system provides satisfactory writing suggestions for English as a Second Language (ESL) learners.

This paper shows the great potential of incorporating different approaches to help writing. Not only did they solve different kinds of writing problems, but also they complement and reinforce each other to be a complete and effective solution. Despite the extensive and multifaceted feedback and suggestion, writing is not all about syntactically or lexically well-written. It involves contents, structure, the certain understanding of the background, and many other factors to compose a rich, organized and sophisticated text. (e.g., conventional structure and idioms in academic writing). There is still a long way to go to accomplish the ultimate goal. We envision the future of writing to be a joyful experience with the help of instantaneous suggestion and constructive feedback.

We introduce a method for learning to translate out-of-vocabulary (OOV) words. The method focuses on combining sublexical/constituent translations of an OOV to generate its translation candidates. In our approach, wild-card searches are formulated based on our OOV analysis, aimed at maximizing the probability of retrieving OOVs’ sublexical translations from existing resource of machine translation (MT) systems. At run-time, translation candidates of the unknown words are generated from their suitable sublexical translations and ranked based on monolingual and bilingual information. We have incorporated the OOV model into a state-of-the-art MT system and experimental results show that our model indeed helps to ease the negative impact of OOVs on translation quality, especially for sentences containing more OOVs (significant improvement).

We introduce a method for learning to find domain-specific translations for a given term on the Web. In our approach, the source term is transformed into an expanded query aimed at maximizing the probability of retrieving translations from a very large collection of mixed-code documents. The method involves automatically generating sets of target-language words from training data in specific domains, automatically selecting target words for effectiveness in retrieving documents containing the sought-after translations. At run time, the given term is transformed into an expanded query and submitted to a search engine, and ranked translations are extracted from the document snippets returned by the search engine. We present a prototype, TermMine, which applies the method to a Web search engine. Evaluations over a set of domains and terms show that TermMine outperforms state-of-the-art machine translation systems.

Named entities make up a bulk of documents. Extracting named entities is crucial to various applications of natural language processing. Although efforts to identify named entities within monolingual documents are numerous, extracting bilingual named entities has not been investigated extensively owing to the complexity of the task. In this paper, we describe a statistical phrase translation model and a statistical transliteration model. Under the proposed models, a new method is proposed to align bilingual named entities in parallel corpora. Experimental results indicate that a satisfactory precision rate can be achieved. To enhance the performance, we also describe how to improve the proposed method by incorporating approximate matching and person name recognition. Experimental results show that performance is significantly improved with the enhancement.

Named-entities in free text represent a challenge to text analysis in Machine Translation and Cross Language Information Retrieval. These phrases are often transliterated into another language with a different sound inventory and writing system. Named-entities found in free text are often not listed in bilingual dictionaries. Although it is possible to identify and translate named-entities on the fly without a list of proper names and transliterations, an extensive list of existing transliterations certainly will ensure high precision rate. We use a seed list of proper names and transliterations to train a Machine Transliteration Model. With the model it is possible to extract proper names and their transliterations in monolingual or parallel corpora with high precision and recall rates.

We present a new approach to the problem of aligning English and Chinese sentences in a bilingual corpus based on adaptive learning. While using length information alone produces surprisingly good results for aligning bilingual French and English sentences with success rates well over 95%, it does not fair as well for the alignment of English and Chinese sentences. The crux of the problem lies in greater variability of lengths and match types of the matched sentences. We propose to cope with such variability via a two-pass scheme under which model parameters can be learned from the data at hand. Experiments show that under the approach bilingual English-Chinese texts can be aligned effectively across diverse domains, genres and translation directions with accuracy rates approaching 99%.

Machine-readable dictionaries have been regarded as a rich knowledge source from which various relations in lexical semantics can be effectively extracted. These semantic relations have been found useful for supporting a wide range of natural language processing tasks, from information retrieval to interpretation of noun sequences, and to resolution of prepositional phrase attachment. In this paper, we address issues related to problems in building a semantic hierarchy from machine-readable dictionaries: genus disambiguation, discovery of covert categories, and bilingual taxonomy. In addressing these issues, we will discuss the limiting factors in dictionary definitions and ways of eradicating these problems. We will also compare the taxonomy extracted in this way from a typical MRD and that of the WordNet. We argue that although the MRD-derived taxonomy is considerably flatter than the WordNet, it nevertheless provides a functional core for a variety of semantic relations and inferences which is vital in natural language processing.