Robustness Versus Fidelity In Natural Language Understanding

نویسندگان

  • Mark G. Core
  • Johanna D. Moore
چکیده

A number of issues arise when trying to scaleup natural language understanding (NLU) tools designed for relatively simple domains (e.g., flight information) to domains such as medical advising or tutoring where deep understanding of user utterances is necessary. Because the subject matter is richer, the range of vocabulary and grammatical structures is larger meaning NLU tools are more likely to encounter out-of-vocabulary words or extra-grammatical utterances. This is especially true in medical advising and tutoring where users may not know the correct vocabulary and use common sense terms or descriptions instead. Techniques designed to improve robustness (e.g., skipping unknown words, relaxing grammatical constraints, mapping unknown words to known words) are effective at increasing the number of utterances for which an NLU subsystem can produce a semantic interpretation. However, such techniques introduce additional ambiguity and can lead to a loss of fidelity (i.e., a mismatch between the semantic interpretation and what the language producer meant). To control this trade-off, we propose semantic interpretation confidence scores akin to speech recognition confidence scores, and describe our initial attempt to compute such a score in a modularized NLU sub-system.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Iranian English Language Teachers’ Perception of Task-based Language Teaching (TBLT) Principles and Challenges to its Implementation

This paper presents the findings of a study on Iranian  English language teachers’ understanding of  Task-based language teaching (TBLT) principles and  perceived challenges of TBLT implementation in Iran. The data obtained from 100 respondents on a 39-item survey instrument and four essay questions analyzed through frequency statistics revealed that nearly 70 percent of teachers are cognizant ...

متن کامل

Hierarchical feature-based translation for scalable natural language understanding

For complex natural language understanding systems with a large number of statistically confusable but semantically different formal commands, there are many difficulties in performing an accurate translation of a user input into a formal command in a single step. This paper addresses scalability issues in natural language understanding, and describes a method for performing the translation in ...

متن کامل

Towards a Robust Deep Language Understanding System

We propose a system that bridges the gap between the two major approaches toward natural language processing: robust shallow text processing and domain-specific (often linguistically-based) deep understanding. We propose to use an existing linguistically motivated deep understanding system as the core and to leverage statistical techniques and external resources such as world knowledge to broad...

متن کامل

Teacher Language Awareness from the Procedural Perspective: The Case of Novice versus Experienced EFL Teachers

Despite the abundance of research on ELT teachers, little is known about teacher language awareness (TLA) with focus on its impact on pedagogical practice in the EFL context. To fill this gap, an in-depth study was conducted to examine the procedural dimension of TLA among eight EFL teachers with different teaching experiences (novice versus experienced) related to teaching grammar at Iranian l...

متن کامل

Cooperative model-based language understanding

In this paper, we propose a novel Cooperative Model for natural language understanding in a dialogue system. We build this based on both Finite State Model (FSM) and Statistical Learning Model (SLM). FSM provides two strategies for language understanding and have a high accuracy but little robustness and flexibility. Statistical approach is much more robust but less accurate. Cooperative Model ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2004