Less is Less: When Are Snippets Insufficient for Human vs Machine Relevance Estimation?

TL;DR

This study investigates when document snippets are sufficient for relevance estimation by humans and neural models, revealing that full text benefits both in certain cases but can also negatively impact ranking performance.

Contribution

It provides a comparative analysis of human and neural model relevance assessments using full text versus snippets, highlighting differing responses and conditions for effectiveness.

Findings

Full text benefits humans and BERT for specific query types

Adding full text can harm ranking performance for navigational queries

Humans and machines respond differently to additional document information

Abstract

Traditional information retrieval (IR) ranking models process the full text of documents. Newer models based on Transformers, however, would incur a high computational cost when processing long texts, so typically use only snippets from the document instead. The model's input based on a document's URL, title, and snippet (UTS) is akin to the summaries that appear on a search engine results page (SERP) to help searchers decide which result to click. This raises questions about when such summaries are sufficient for relevance estimation by the ranking model or the human assessor, and whether humans and machines benefit from the document's full text in similar ways. To answer these questions, we study human and neural model based relevance assessments on 12k query-documents sampled from Bing's search logs. We compare changes in the relevance assessments when only the document summaries and when the full text is also exposed to assessors, studying a range of query and document properties, e.g., query type, snippet length. Our findings show that the full text is beneficial for humans and a BERT model for similar query and document types, e.g., tail, long queries. A closer look, however, reveals that humans and machines respond to the additional input in very different ways. Adding the full text can also hurt the ranker's performance, e.g., for navigational queries.