big difference between setting title and not setting title

[Jeffwan]

We are using cross decoder to rerank the results. for some QA pairs. We use following format to get the ranking scores.

<query, para1, title1>
<query, para2, title2>
<query, para3, title3>

model.matching(query: List[str], para: List[str], title: List[str])

There's one observation I notice is, for the same question, setting title give me much better results, top1 or top2. However, If I do not set title, it is really bad (~top10 for 20 records).

I am curious why title makes a big difference here? In my case, for query, we have many tiles with same name. I felt adding title is not a big deal but it is

[Jeffwan]

RocketQA/rocketqa/encoder/cross_encoder.py

Lines 160 to 166 in 1746b93

	if len(title) != 0:
	assert len(para) == len(title)
	for q, t, p in zip(query, title, para):
	data.append(q + '\t' + t + '\t' + p)
	else:
	for q, p in zip(query, para):
	data.append(q + '\t\t' + p)