Experience Grounds Language

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 8718–8735, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 8718 Experience Grounds Language Yonatan Bisk* Ari Holtzman* Jesse Thomason* Jacob Andreas Yoshua Bengio Joyce Chai Mirella Lapata Angeliki Lazaridou Jonathan May Aleksandr Nisnevich Nicolas Pinto Joseph Turian Abstract Language understanding research is held back by a failure to relate language to the physical world it describes and to the social interactions it facilitates. Despite the incredible effective- ness of language processing models to tackle tasks after being trained on text alone, success- ful linguistic communication relies on a shared experience of the world. It is this shared expe- rience that makes utterances meaningful. Natural language processing is a diverse field, and progress throughout its development has come from new representational theories, mod- eling techniques, data collection paradigms, and tasks. We posit that the present success of representation learning approaches trained on large, text-only corpora requires the paral- lel tradition of research on the broader physi- cal and social context of language to address the deeper questions of communication. Improvements in hardware and data collection have galvanized progress in NLP across many benchmark tasks. Impressive performance has been achieved in language modeling (Radford et al., 2019; Zellers et al., 2019b; Keskar et al., 2019) and span-selection question answering (Devlin et al., 2019; Yang et al., 2019b; Lan et al., 2020) through massive data and massive models. With models exceeding human performance on such tasks, now is an excellent time to reflect on a key question: Where is NLP going? In this paper, we consider how the data and world a language learner is exposed to define and con- strains the scope of that learner’s semantics. Mean- ing does not arise from the statistical distribution of words, but from their use by people to communi- cate. Many of the assumptions and understandings on which communication relies lie outside of text. We must consider what is missing from models Meaning is not a unique property of language, but a general characteristic of human activity ... We cannot say that each morpheme or word has a single or central meaning, or even that it has a continuous or coherent range of meanings ... there are two separate uses and meanings of language – the concrete ... and the abstract. Zellig S. Harris (Distributional Structure 1954) trained solely on text corpora, even when those cor- pora are meticulously annotated or Internet-scale. You can’t learn language from the radio. Nearly every NLP course will at some point make this claim. The futility of learning language from lin- guistic signal alone is intuitive, and mirrors the belief that humans lean deeply on non-linguistic knowledge (Chomsky, 1965, 1980). However, as a field we attempt this futility: trying to learn lan- guage from the Internet, which stands in as the modern radio to deliver limitless language. In this piece, we argue that the need for language to attach to “extralinguistic events" (Ervin-Tripp, 1973) and the requirement …

Content truncated to 500 words