Cross Sentence Inference for Process Knowledge

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1442–1451, Austin, Texas, November 1-5, 2016. c⃝2016 Association for Computational Linguistics Cross-Sentence Inference for Process Knowledge Samuel Louvan+, Chetan Naik+, Sadhana Kumaravel+, Heeyoung Kwon+, Niranjan Balasubramanian+, Peter Clark∗ +Stony Brook University, ∗Allen Institute for AI, {slouvan, cnaik, skumaravel, heekwon,niranjan}@cs.stonybrook.edu, peterc@allenai.org Abstract For AI systems to reason about real world situ- ations, they need to recognize which processes are at play and which entities play key roles in them. Our goal is to extract this kind of role- based knowledge about processes, from mul- tiple sentence-level descriptions. This knowl- edge is hard to acquire; while semantic role labeling (SRL) systems can extract sentence level role information about individual men- tions of a process, their results are often noisy and they do not attempt create a globally con- sistent characterization of a process. To overcome this, we extend standard within sentence joint inference to inference across multiple sentences. This cross sentence in- ference promotes role assignments that are compatible across different descriptions of the same process. When formulated as an Integer Linear Program, this leads to improvements over within-sentence inference by nearly 3% in F1. The resulting role-based knowledge is of high quality (with a F1 of nearly 82). 1 Introduction Knowledge about processes is essential for AI sys- tems in order to understand and reason about the world. At the simplest level, even knowing which class of entities play key roles can be useful for tasks involving recognition and reasoning about pro- cesses. For instance, given a description “a pud- dle drying in the sun”, one can recognize this as an instance of the process evaporation using a macro- level role knowledge: Among others, the typical un- dergoer of evaporation is a kind of liquid (the pud- 1) Evaporation is the process by which liquids are converted to their gaseous forms. 2) Evaporation is the process by which water is converted into water vapor. 3) Water vapor rises from water due to evaporation. 4) Clouds arise as water evaporates in the sun. Table 1: Example sentences for the process evaporation. Un- derlined spans correspond to fillers for the undergoer role. dle), and the enabler is usually a heat source (the sun). Our goal is to acquire this kind of role-based knowledge about processes from sentence-level de- scriptions in grade level texts. Semantic role label- ing (SRL) systems can be trained to identify these process specific roles. However, these were de- veloped for sentence-level interpretation and only ensure within sentence consistency of labels (Pun- yakanok et al., 2004; Toutanova et al., 2005; Lewis et al., 2015), limiting their ability to generate co- herent characterizations of the process overall. In particular, the same process participant may appear in text at different syntactic positions, with different wording, and with different verbs, which makes it hard to extract globally consistent descriptions. In this work, we propose a cross sentence inference method to address this problem. To illustrate the challenge consider some exam- …

Content truncated to 500 words