Minor adjustment in discussion

CodingTil · Nov 14, 2023 · 4b83878 · 4b83878
1 parent c6b002e
commit 4b83878
Show file tree

Hide file tree

Showing 2 changed files with 1 addition and 1 deletion.
diff --git a/report/main.pdf b/report/main.pdf
diff --git a/report/main.tex b/report/main.tex
@@ -265,7 +265,7 @@ \section{Discussion and Conclusions}
 
 Our findings further highlight the advantages of extending the baseline approach. Incorporating either a query expansion or a document expansion mechanism significantly enhances the quality of document rankings across all evaluated metrics. Interestingly, combining both the query and document expansion elements didn't consistently yield expected improvements. One plausible explanation centers on our initial sparse retrieval stage, that is \texttt{BM25}. From a semantic viewpoint, this stage may be insufficient in recognizing relevant documents that possess syntactic deviations from the query. Hence, even with the aid from \texttt{doc2query} and \texttt{RM3}, there's potential room for missing relevant documents.
 
-If our theory holds, introducing a dense retrieval technique, like \texttt{ANCE}, see Section \ref{sec:ance}, might bridge this semantic gap, refining the precision of document rankings. Additionally, it's worth exploring the reason behind the performance dip of the \texttt{doc2query} + \texttt{RM3} strategy in the mean reciprocal rank metric, especially when compared against the results from the baseline + \texttt{RM3} and sole \texttt{doc2query} methods.
+If our theory holds, introducing a dense retrieval technique, like \texttt{ANCE}, see Section \ref{sec:ance}, might bridge this semantic gap, refining the precision of document rankings. Additionally, it's worth exploring the reason behind the performance dip of the \texttt{doc2query} + \texttt{RM3} strategy in all metrics when compared against the results from the \texttt{doc2query} method, as one would expect the combination of document expansion and query expansion to perform at least as well as the individual methods.
 
 In conclusion, while infusing both query and document expansion strategies substantially boosts retrieval quality, the benefits aren't without implications. The bright side is that these enhancements introduce insignificant extra computational costs during retrieval, showcasing a practical approach for improving conversational retrieval systems.