Natural Language Programming: Turning Texts into Executable Code

Speaker:
Reut Tsarfaty - GUEST LECTURE
Date:
Tuesday, 8.1.2019, 10:30
Place:
Room 201 Taub Bld.
Affiliation:
The ONLP lab, Faculty of Mathematics and Computer Science, The Open University of Israel
Host:
Eran Yahav

Can we program computers in our native tongue? This idea, termed natural language programming (NLPRO), has attracted attention almost since the inception of computers themselves. From the point of view of software engineering (SE), efforts to program in natural language (NL) have relied thus far on controlled natural languages (CNL) -- small unambiguous fragments of English with restricted grammars and limited expressivity. Is it possible to replace these CNLs with truly natural, human language? From the point of view of natural language processing (NLP), current technology successfully extracts static information from NL texts. However, the level of NL understanding required for programming in NL goes far beyond such information extraction. Is it possible to endow computers with a dynamic kind of NL understanding? In this talk I argue that the solutions to these seemingly separate challenges are actually closely intertwined, and that one community's challenge is the other community's stepping stone for a huge leap and vice versa. Specifically, in this talk I propose to view executable programs in SE as semantic structures in NLP, as the basis for broad-coverage semantic parsing. I present a feasibility study on the semantic parsing of requirements documents into executable scenarios, where the requirements are written in a restricted yet highly ambiguous fragment of English, and the target representation employs live sequence charts (LSC), a multi-modal executable programming language. The parsing architecture I propose jointly models sentence-level and discourse-level processing in a generative probabilistic framework. I empirically show that the discourse-based model consistently outperforms the sentence-based model, constructing a system that reflects both the static (entities, properties) and dynamic (behavioral scenarios) requirements in the input document. BIO: ==== Dr. Reut Tsarfaty is a senior lecturer at the department of Mathematics and Computer Science at the Open University in Israel, and the head of the ONLP research lab. Reut holds a BSc. from the Technion in Israel and MSc./PhD. from the Institute for Logic, Language and Computation (ILLC) at the University of Amsterdam. She also held postdoctoral research fellowships at Uppsala University in Sweden and at the Weizmann Institute in Israel. Reut holds an ERC staring grant, an ISF individual grant, and she previously held a MOSAIC NWO grant (Dutch Science Foundation). Her research focuses on statistical parsing, broadly interpreted to cover morphological, syntactic and semantic parsing, and she is an expert on parsing morphologically rich languages. Reut and her students also research NLP/AI application domains, including (but not limited to) natural language programming, automated essay scoring, and natural talkback generation.

Back to the index of events