Related papers: What Makes a Good Paraphrase: Do Automated Evaluat…
Linguistically diverse datasets are critical for training and evaluating robust machine learning systems, but data collection is a costly process that often requires experts. Crowdsourcing the process of paraphrase generation is an…
Automatic machine translation metrics typically rely on human translations to determine the quality of system translations. Common wisdom in the field dictates that the human references should be of very high quality. However, there are no…
Modern NLP defines the task of style transfer as modifying the style of a given sentence without appreciably changing its semantics, which implies that the outputs of style transfer systems should be paraphrases of their inputs. However,…
Artificial intelligence systems exhibit many useful capabilities, but they appear to lack understanding. This essay describes how we could go about constructing a machine capable of understanding. As John Locke (1689) pointed out words are…
Paraphrasing is a useful natural language processing task that can contribute to more diverse generated or translated texts. Natural language inference (NLI) and paraphrasing share some similarities and can benefit from a joint approach. We…
We introduce Parallel Paraphrasing ($\text{Para}_\text{both}$), an augmentation method for translation metrics making use of automatic paraphrasing of both the reference and hypothesis. This method counteracts the typically misleading…
Comprehending lyrics, as found in songs and poems, can pose a challenge to human and machine readers alike. This motivates the need for systems that can understand the ambiguity and jargon found in such creative texts, and provide…
Many NLP tasks require to automatically identify the most significant words in a text. In this work, we derive word significance from models trained to solve semantic task: Natural Language Inference and Paraphrase Identification. Using an…
We investigate a long-perceived shortcoming in the typical use of BLEU: its reliance on a single reference. Using modern neural paraphrasing techniques, we study whether automatically generating additional diverse references can provide…
This dissertation explores the linguistic and computational aspects of the meaning relations that can hold between two or more complex linguistic expressions (phrases, clauses, sentences, paragraphs). In particular, it focuses on…
Though generative dialogue modeling is widely seen as a language modeling task, the task demands an agent to have a complex natural language understanding of its input text to carry a meaningful interaction with an user. The automatic…
Reliable evaluation protocols are of utmost importance for reproducible NLP research. In this work, we show that sometimes neither metric nor conventional human evaluation is sufficient to draw conclusions about system performance. Using…
Preparing exact and comprehensive word meaning explanations is one of the key steps in the process of monolingual dictionary writing. In standard methodology, the explanations need an expert lexicographer who spends a substantial amount of…
When faced with a large number of product reviews, it is not clear that a human can remember all of them and weight opinions representatively to write a good reference summary. We propose an automatic metric to test the prevalence of the…
Topic models extract representative word sets - called topics - from word counts in documents without requiring any semantic annotations. Topics are not guaranteed to be well interpretable, therefore, coherence measures have been proposed…
Providing natural language explanations for recommendations is particularly useful from the perspective of a non-expert user. Although several methods for providing such explanations have recently been proposed, we argue that an important…
A paraphrase is a restatement of the meaning of a text in other words. Paraphrases have been studied to enhance the performance of many natural language processing tasks. In this paper, we propose a novel task iParaphrasing to extract…
We consider the problem of learning general-purpose, paraphrastic sentence embeddings in the setting of Wieting et al. (2016b). We use neural machine translation to generate sentential paraphrases via back-translation of bilingual sentence…
The Split and Rephrase (SPRP) task, which consists in splitting complex sentences into a sequence of shorter grammatical sentences, while preserving the original meaning, can facilitate the processing of complex texts for humans and…
Conversational AI assistants are becoming popular and question-answering is an important part of any conversational assistant. Using relevant utterances as features in question-answering has shown to improve both the precision and recall…